© 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. 34-GEMMASCOPE-RES-131K
    7. 58099
    Prev
    Next
    INDEX
    Explanations

    code and metadata files

    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_34/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
    //{
    -0.83
    ußen
    -0.77
     Misalnya
    -0.72
    Ǜ
    -0.72
     Penyakit
    -0.72
    波
    -0.71
    HIB
    -0.71
    CTX
    -0.70
     Manfaat
    -0.70
     čás
    -0.69
    POSITIVE LOGITS
     Bala
    0.76
     Balla
    0.76
    と思いますが
    0.74
     continuar
    0.70
    uits
    0.69
    艉
    0.67
    Bala
    0.67
    iante
    0.66
    TableData
    0.66
    lotz
    0.65
    Activations Density 0.019%

    No Known Activations