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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98413
    Prev
    Next
    INDEX
    Explanations

    code file paths and descriptions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Hong
    -0.75
     accountId
    -0.74
     Freitas
    -0.69
     interessieren
    -0.66
    肯定
    -0.66
     mediation
    -0.65
    Zeus
    -0.65
     Queen
    -0.65
     čaj
    -0.64
     polegadas
    -0.63
    POSITIVE LOGITS
    identes
    0.72
     Swit
    0.70
     Morn
    0.65
    atella
    0.65
     bille
    0.65
     समीक्षा
    0.64
     Walther
    0.63
     stabile
    0.63
     obligator
    0.63
    integrate
    0.61
    Activations Density 0.088%

    No Known Activations