© 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. 216105
    Prev
    Next
    INDEX
    Explanations

    alignedclick

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

    INT :=, eventual formation, still looks

    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
     ઝ
    0.46
    腎
    0.44
    hình
    0.43
     ぞ
    0.43
    ー
    0.43
    槓
    0.43
    革命
    0.43
    品種
    0.43
    栢
    0.43
     গেছে
    0.42
    POSITIVE LOGITS
     escritorio
    0.48
     exceso
    0.47
     increase
    0.47
     incendio
    0.46
     tanda
    0.46
     exclusivo
    0.46
     exclusiva
    0.46
     pracę
    0.46
     kritik
    0.45
     Fraction
    0.45
    Activations Density 0.001%

    No Known Activations