© 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. 107038
    Prev
    Next
    INDEX
    Explanations

    programming code structures

    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
     面包
    -1.34
    Hermoso
    -1.30
    总之
    -1.29
    吶
    -1.28
    お話
    -1.28
     作り方
    -1.26
    Приготовление
    -1.21
    Obviously
    -1.20
     经典
    -1.20
     noteworthy
    -1.19
    POSITIVE LOGITS
    Ꮴ
    1.56
    tagHelper
    1.40
    DebuggerNonUser
    1.38
    riam
    1.36
    ată
    1.34
    ViewFeatures
    1.34
     Eſ
    1.31
     cepillo
    1.27
     ܙ
    1.27
    tivity
    1.25
    Activations Density 0.225%

    No Known Activations