© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6442
    Prev
    Next
    INDEX
    Explanations

    programming and queries

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

    The neuron is specialized in detecting sentence‐ending punctuation (e.g. periods and similar terminal marks).

    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
     CHE
    0.84
    ״
    0.82
     SPACE
    0.81
     STARS
    0.81
    ’
    0.81
     SHOP
    0.79
     HILL
    0.79
     VALLEY
    0.77
     POINT
    0.76
     OPPORT
    0.76
    POSITIVE LOGITS
    довой
    0.79
    говой
    0.76
    ា
    0.75
     совпада
    0.75
    дные
    0.74
    ма
    0.74
     обраща
    0.74
     მხოლოდ
    0.73
    direccion
    0.73
    дна
    0.73
    Activations Density 0.000%

    No Known Activations