© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43120
    Prev
    Next
    INDEX
    Explanations

    code segments and specific symbols

    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
    みんなで
    -1.56
    ときに
    -1.52
    車で
    -1.52
    ときの
    -1.48
     Of
    -1.48
    お待ちしております
    -1.46
    Of
    -1.45
    ta
    -1.45
    車が
    -1.44
     to
    -1.43
    POSITIVE LOGITS
    、
    1.53
     biblioteca
    1.50
     Capitán
    1.44
     孫
    1.37
     colonia
    1.31
    ي
    1.30
     pousada
    1.30
    מ
    1.30
    requipa
    1.29
     misteriosa
    1.29
    Activations Density 0.015%

    No Known Activations