© 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. 11004
    Prev
    Next
    INDEX
    Explanations

    mathematical and group structures

    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
    ruptcy
    -0.93
     gött
    -0.92
    contrato
    -0.88
    kelt
    -0.85
    mmung
    -0.83
    ellä
    -0.83
    热情
    -0.82
     getY
    -0.79
    liyor
    -0.79
     überall
    -0.79
    POSITIVE LOGITS
     acompañada
    0.89
    Only
    0.86
    only
    0.85
    Ici
    0.85
     condado
    0.85
    GRAPHIC
    0.84
     klara
    0.83
     only
    0.81
    辄
    0.80
     Only
    0.79
    Activations Density 0.034%

    No Known Activations