© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7971
    Prev
    Next
    INDEX
    Explanations

    groups and organizations

    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
     inspiration
    -1.67
    ⚣
    -1.63
    來
    -1.61
     alebo
    -1.60
    También
    -1.60
    鸶
    -1.59
     trouvera
    -1.57
     magnificent
    -1.57
     учеб
    -1.55
     planet
    -1.53
    POSITIVE LOGITS
     of
    2.08
     formado
    1.73
    <bos>
    1.61
    _
    1.59
     möjlighet
    1.55
     despite
    1.45
     vilken
    1.42
     nying
    1.41
     spelar
    1.41
    }
    1.41
    Activations Density 0.087%

    No Known Activations