© 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. 14108
    Prev
    Next
    INDEX
    Explanations

    song lyrics

    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
     niebla
    -1.42
    vantaged
    -1.31
     carcasa
    -1.29
    슐
    -1.29
    adeira
    -1.29
    iços
    -1.27
     巧克力
    -1.27
     privada
    -1.27
    而且
    -1.26
    靣
    -1.26
    POSITIVE LOGITS
     lyrics
    1.39
     [][]
    1.35
     namorados
    1.28
     newly
    1.23
     both
    1.20
     some
    1.20
    :“
    1.20
     Ergän
    1.16
    護士
    1.16
     Publicado
    1.16
    Activations Density 0.026%

    No Known Activations