Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38559
    Prev
    Next
    INDEX
    Explanations

    css classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    el
    1.73
    ic
    1.50
    ar
    1.48
    al
    1.47
    ot
    1.47
    on
    1.27
    m
    1.25
    in
    1.24
    ert
    1.23
    il
    1.22
    POSITIVE LOGITS
    ない
    1.67
    Ꮓ
    1.45
    {
    1.41
    WY
    1.41
    ISHING
    1.41
    Zara
    1.39
    IAL
    1.38
    वर
    1.32
    Fre
    1.31
    CTION
    1.30
    Activations Density 0.009%

    No Known Activations