© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215269
    Prev
    Next
    INDEX
    Explanations

    identity, control, depicting

    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_40_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
     rewire
    0.40
    日
    0.37
    ᅩ
    0.37
    型
    0.37
    ทย
    0.36
    digital
    0.36
    ठभे
    0.36
     waitFor
    0.36
    nights
    0.36
     Tshirt
    0.35
    POSITIVE LOGITS
     आसानी
    0.52
    Hor
    0.46
    涣
    0.44
    Separ
    0.42
    Its
    0.41
    Probably
    0.40
    ാരം
    0.38
     Hor
    0.38
    Tokens
    0.38
     Staaten
    0.37
    Activations Density 0.000%

    No Known Activations