© 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. 71949
    Prev
    Next
    INDEX
    Explanations

    language detection and context

    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
    蠵
    -2.66
     erhi
    -2.64
    🛇
    -2.59
     somewhat
    -2.58
    峁
    -2.56
     of
    -2.56
    🫅
    -2.42
    罍
    -2.38
    嫫
    -2.38
     maquilla
    -2.30
    POSITIVE LOGITS
    When
    3.17
    Why
    2.75
     When
    2.73
    How
    2.69
    Perhaps
    2.59
    Even
    2.59
    what
    2.56
    Although
    2.56
    There
    2.55
    While
    2.55
    Activations Density 0.002%

    No Known Activations