© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9381
    Prev
    Next
    INDEX
    Explanations

    compared to

    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
    一惊
    -0.98
    猫咪
    -0.91
     Coleoptera
    -0.90
    tive
    -0.89
     LINE
    -0.88
    有可能
    -0.85
    Externé
    -0.84
    终极
    -0.84
    叹了口气
    -0.84
     djur
    -0.84
    POSITIVE LOGITS
     міста
    0.96
     noting
    0.95
    casus
    0.94
     levantar
    0.93
     soltar
    0.93
     geschickt
    0.90
     cortar
    0.89
    gantian
    0.88
    ֝
    0.87
    velope
    0.86
    Activations Density 0.087%

    No Known Activations