© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4936
    Prev
    Next
    INDEX
    Explanations

    commands and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     кни
    1.07
     окра
    1.06
    引
    1.02
     syndicated
    1.01
     предостав
    0.97
     обуча
    0.95
     Люд
    0.93
    essay
    0.92
     rét
    0.91
     бабу
    0.89
    POSITIVE LOGITS
    mena
    1.22
    ∓
    1.18
    acil
    1.10
    殊
    1.10
    取る
    1.10
     Davido
    1.08
    の違い
    1.08
     suffix
    1.08
    sime
    1.07
    排除
    1.07
    Activations Density 0.059%

    No Known Activations