© 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. 15159
    Prev
    Next
    INDEX
    Explanations

    listing bedrooms and bathrooms

    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
     to
    -1.73
    </h4>
    -1.60
     they
    -1.41
     tersenyum
    -1.39
     mengucap
    -1.29
    corrhi
    -1.28
     terdengar
    -1.27
     они
    -1.27
    كويكب
    -1.27
     onsdag
    -1.26
    POSITIVE LOGITS
     geladeira
    1.27
    經過
    1.18
     тільки
    1.18
    囂
    1.16
     خودش
    1.16
     personalización
    1.14
     will
    1.13
    LANTA
    1.12
     notre
    1.11
     流れ
    1.11
    Activations Density 0.007%

    No Known Activations