© 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. 146662
    Prev
    Next
    INDEX
    Explanations

    determination ofWT butincluding theshattered atbeen exemptfollowing hisfor lunchhome to

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

    understanding context and relationships

    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
    Negative Logits
    樞
    0.48
    
    0.46
    ύν
    0.45
    ('|
    0.44
    最大
    0.42
     среду
    0.42
    謨
    0.42
    يد
    0.41
    缕
    0.41
    န်း
    0.40
    POSITIVE LOGITS
     pengg
    0.52
    essori
    0.49
     risotto
    0.47
     pendekatan
    0.45
     perhitungan
    0.45
     Aus
    0.45
    tting
    0.45
    dokter
    0.45
    awar
    0.43
     nigg
    0.43
    Activations Density 0.000%

    No Known Activations