© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205537
    Prev
    Next
    INDEX
    Explanations

    model, failures, players, films, editor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    spraak
    0.48
    сцю
    0.46
    claimed
    0.46
    illent
    0.46
    ప
    0.45
    resultado
    0.45
    Auch
    0.45
    十二章
    0.45
    Contribution
    0.45
     শোনা
    0.45
    POSITIVE LOGITS
     săn
    0.48
     Aes
    0.47
     quell
    0.46
     Antip
    0.46
     buying
    0.45
     markets
    0.44
    ,
    0.43
     relieve
    0.43
     buys
    0.43
     M
    0.43
    Activations Density 0.001%

    No Known Activations