© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28588
    Prev
    Next
    INDEX
    Explanations

    description or introduction sections

    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
     muhimu
    -0.81
     utaf
    -0.77
    elve
    -0.73
     So
    -0.73
    RTLI
    -0.73
     字母
    -0.73
    gheny
    -0.73
     貓
    -0.72
    Moreover
    -0.72
    нит
    -0.72
    POSITIVE LOGITS
    骤
    0.88
     poches
    0.88
     działalności
    0.87
    鑭
    0.85
     région
    0.85
    JW
    0.85
     ПК
    0.84
    IMAN
    0.84
    atud
    0.83
    GAM
    0.82
    Activations Density 0.325%

    No Known Activations