© 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. 27903
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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
    liert
    -1.01
     cinturón
    -0.94
     while
    -0.90
     kağıdı
    -0.90
    っていると
    -0.88
    herbe
    -0.88
     tutaj
    -0.87
     тогда
    -0.86
     hoặc
    -0.85
     moje
    -0.85
    POSITIVE LOGITS
    Boh
    0.95
     kuni
    0.93
    Nuc
    0.89
    珠宝
    0.87
    Ced
    0.84
     ganger
    0.83
     gange
    0.82
     Это
    0.82
    崛
    0.82
    Lí
    0.81
    Activations Density 0.002%

    No Known Activations