© 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. 34-GEMMASCOPE-RES-131K
    4. 118142
    Prev
    Next
    INDEX
    Explanations

    graphic and mathematical representations

    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
     retroactive
    -0.77
    pheus
    -0.75
    ilistic
    -0.73
    neurial
    -0.70
     順
    -0.68
     interpolation
    -0.67
    騫
    -0.67
     рады
    -0.66
    doctoral
    -0.66
    吏
    -0.66
    POSITIVE LOGITS
    graphic
    0.77
    checks
    0.76
    graphs
    0.75
    erman
    0.71
    Checks
    0.71
    的设计
    0.71
    ায়
    0.70
    ickson
    0.69
     imprim
    0.69
     getSystem
    0.69
    Activations Density 0.067%

    No Known Activations