© 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. 14657
    Prev
    Next
    INDEX
    Explanations

    academic and technical terms

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

    This neuron strongly activates on tokens that start a new sentence (i.e. sentence-initial words).

    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
    redni
    0.86
    日曜
    0.81
    a
    0.79
    u
    0.78
    l
    0.78
    ыл
    0.77
    na
    0.77
    gpt
    0.76
     hvad
    0.75
    ഋ
    0.74
    POSITIVE LOGITS
     Energies
    0.80
    कुर
    0.77
     Palazzo
    0.74
     battaglia
    0.72
     legno
    0.72
     wichtigsten
    0.71
     seguito
    0.71
     կ
    0.70
     Tunis
    0.70
     Life
    0.69
    Activations Density 0.000%

    No Known Activations