© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27288
    Prev
    Next
    INDEX
    Explanations

    code snippets and keywords

    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
    Lots
    -0.90
     rẻ
    -0.89
    感じが
    -0.88
     deleted
    -0.88
     gone
    -0.88
     graciosos
    -0.87
     ANOTHER
    -0.87
    continue
    -0.85
     also
    -0.85
     مقابل
    -0.83
    POSITIVE LOGITS
     was
    0.97
    ombies
    0.95
    šanu
    0.91
    ティング
    0.88
    setFilter
    0.87
    ociação
    0.86
    =").
    0.84
    ="%
    0.83
    Leary
    0.82
     said
    0.82
    Activations Density 0.001%

    No Known Activations