© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56922
    Prev
    Next
    INDEX
    Explanations

    Kōwankyoku, Kōzuke, Kōno

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    utom
    -0.82
    cuadro
    -0.82
    قص
    -0.82
    帳
    -0.79
    Alemania
    -0.75
     manzanas
    -0.75
     scares
    -0.75
    學院
    -0.74
    トーン
    -0.74
    スタイル
    -0.73
    POSITIVE LOGITS
    ICOLON
    0.82
     they
    0.81
    hicle
    0.80
    heres
    0.79
    half
    0.73
    INGHAM
    0.73
    ELTS
    0.73
    VING
    0.72
     leading
    0.72
    leading
    0.71
    Activations Density 0.015%

    No Known Activations