© 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. 10-GEMMASCOPE-RES-131K
    7. 104785
    Prev
    Next
    INDEX
    Explanations

    publication

    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
     povezave
    -1.88
     jiné
    -1.73
     aparentemente
    -1.68
    两人的
    -1.66
     соответствии
    -1.65
    わずか
    -1.62
     that
    -1.60
     respirar
    -1.59
    اااا
    -1.59
    نور
    -1.56
    POSITIVE LOGITS
    COLOG
    2.14
    她
    1.74
    ℟
    1.67
     boletín
    1.66
     signifies
    1.63
     Saltar
    1.62
    この
    1.60
    我的
    1.59
    这样
    1.59
     was
    1.58
    Activations Density 0.002%

    No Known Activations