© 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. 69824
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    ्रिया
    -0.79
    années
    -0.72
    ＮＡ
    -0.68
     adjustment
    -0.67
    痛
    -0.67
     తె
    -0.66
    Finalmente
    -0.66
     adjusted
    -0.65
     AssertionError
    -0.65
    SMART
    -0.65
    POSITIVE LOGITS
     Solver
    0.71
    درمان
    0.68
    Открыть
    0.68
    回想
    0.68
    ليق
    0.67
     solver
    0.66
    fährt
    0.65
    驅
    0.65
     anyone
    0.63
    アシ
    0.63
    Activations Density 0.037%

    No Known Activations