© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4751
    Prev
    Next
    INDEX
    Explanations

    specific data concepts

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

    This neuron detects words that occur at the ends of sentences or clauses (i.e., sentence-final tokens).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     -
    0.85
     gemäß
    0.82
    '
    0.80
     ،
    0.80
     بقول
    0.77
     такой
    0.77
    зыва
    0.73
     foolproof
    0.73
     tough
    0.73
    sekten
    0.73
    POSITIVE LOGITS
    ті
    0.95
     résident
    0.90
    enregistrement
    0.83
     Règ
    0.81
     travailler
    0.79
    સ
    0.78
    ኛ
    0.78
     tirer
    0.77
    裵
    0.77
    minecraft
    0.76
    Activations Density 0.000%

    No Known Activations