© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38805
    Prev
    Next
    INDEX
    Explanations

    aid, assistance, subsidies

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mélange
    -1.56
    il
    -1.53
     και
    -1.52
    ጀ
    -1.51
    '
    -1.49
    ☆、
    -1.49
    ｺ
    -1.49
    你在
    -1.48
    erapeu
    -1.48
    end
    -1.48
    POSITIVE LOGITS
     to
    2.27
     such
    1.73
     molte
    1.72
     aspetto
    1.67
     THERE
    1.60
     aiuto
    1.59
     meravigli
    1.55
     applicazione
    1.52
     azione
    1.52
    ÑOS
    1.52
    Activations Density 0.034%

    No Known Activations