© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    used as a variable or property

    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
     sapat
    -0.87
     eden
    -0.84
     palme
    -0.83
     Grandes
    -0.80
    EndOf
    -0.78
    <0x80>
    -0.78
    スポンサーリンク
    -0.77
     Horas
    -0.77
     GRANDE
    -0.77
    reté
    -0.77
    POSITIVE LOGITS
     nekaj
    0.95
    who
    0.87
    Então
    0.82
    hilation
    0.82
     нержа
    0.80
    އ
    0.79
     realms
    0.78
     sleek
    0.78
    чам
    0.78
    into
    0.77
    Activations Density 0.008%

    No Known Activations