© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 149770
    Prev
    Next
    INDEX
    Explanations

    buy a

    np_acts-logits-general · gemini-2.5-flash-lite

    photography and international words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sky
    0.46
    院
    0.46
    Stage
    0.45
    Consider
    0.45
    Frequently
    0.44
    Going
    0.44
    量
    0.44
    Ever
    0.44
    Regist
    0.44
    Festival
    0.43
    POSITIVE LOGITS
     lɛ
    0.59
     ポケット
    0.56
     คลิ
    0.56
     気
    0.55
     wyk
    0.53
     写真
    0.52
     ユ
    0.52
     キャラ
    0.51
     ដ
    0.50
     ກ
    0.50
    Activations Density 0.000%

    No Known Activations