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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8580
    Prev
    Next
    INDEX
    Explanations

    code snippets and explanations

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

    This neuron is highly sensitive to punctuation marks (commas, periods, semicolons, question marks) that delimit clauses or sentences.

    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_31_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
    дцать
    0.81
    ಬ್
    0.78
     Amerikan
    0.76
     Mayıs
    0.73
    ка
    0.72
    ور
    0.72
    ಾ
    0.71
     الموس
    0.71
     Şubat
    0.71
    ע
    0.71
    POSITIVE LOGITS
     estremamente
    0.71
    Halo
    0.69
    Hola
    0.68
    🍽
    0.66
    dining
    0.65
    Além
    0.65
    Excelente
    0.64
    {"
    0.64
    Flexible
    0.64
    Grazie
    0.63
    Activations Density 0.000%

    No Known Activations