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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 38630
    Prev
    Next
    INDEX
    Explanations

    support for policies

    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
     EQS
    1.07
    𝗰
    1.07
     Anatom
    1.05
     Decision
    1.04
     এছাড়া
    1.02
     Disbursement
    1.00
     tucked
    1.00
     Mamata
    1.00
     IMDb
    0.96
     Jour
    0.95
    POSITIVE LOGITS
    ’
    1.19
    IO
    1.17
    但不
    1.16
    ीडियो
    1.09
    рано
    1.06
    엡
    1.06
     étendue
    1.05
    정
    1.05
    ना
    1.04
    ${
    1.03
    Activations Density 0.001%

    No Known Activations