© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    following prepositions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specifically detecting floating-point numerical tokens (numbers with decimal points).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    references to legal documents or sections that are detailed elsewhere in the document.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    formal legalistic or bureaucratic document language, especially section headers and set-phrase provisions within contracts and policies.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Translational
    0.92
     Posterior
    0.85
     Receivable
    0.84
     Postgraduate
    0.81
    क्षिप्त
    0.79
     Neuroscience
    0.79
     Boosting
    0.79
     Astrophys
    0.77
    ерт
    0.76
    m
    0.75
    POSITIVE LOGITS
     direitos
    0.89
     וא
    0.86
     ҳ
    0.82
     perdagangan
    0.81
    すすめ
    0.79
     iguais
    0.75
     империи
    0.73
     pernikahan
    0.73
    会在
    0.71
     casamento
    0.71
    Activations Density 0.000%

    No Known Activations