© 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. 22-GEMMASCOPE-RES-131K
    7. 129519
    Prev
    Next
    INDEX
    Explanations

    php and aspx web 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_22/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
     a
    -1.48
     Only
    -1.32
    llten
    -1.16
    T
    -1.12
     At
    -1.11
    arious
    -1.09
    /*!
    -1.09
    国家的
    -1.07
    获取
    -1.07
     and
    -1.07
    POSITIVE LOGITS
    jangkau
    1.17
    ⽬
    1.16
    angkut
    1.16
     ibadah
    1.16
     Remy
    1.16
    Kde
    1.16
    sistence
    1.15
     puasa
    1.14
    気持ちが
    1.13
    最強
    1.13
    Activations Density 0.007%

    No Known Activations