© 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. 34-GEMMASCOPE-RES-131K
    7. 2352
    Prev
    Next
    INDEX
    Explanations

    code or URLs

    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
    worn
    -0.69
     २
    -0.66
    parseInt
    -0.66
    örande
    -0.66
    Successfully
    -0.66
     Hein
    -0.65
    sidebar
    -0.64
    interes
    -0.64
    Side
    -0.63
    Pago
    -0.63
    POSITIVE LOGITS
    不过是
    0.77
     rescu
    0.75
    david
    0.72
    reme
    0.71
     sanitarias
    0.70
    jącą
    0.68
    物は
    0.68
    ᆫ
    0.66
    acio
    0.66
    toxins
    0.66
    Activations Density 0.050%

    No Known Activations