© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2916
    Prev
    Next
    INDEX
    Explanations

    JSON structure or code snippets

    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
     extension
    -0.83
    EXTENSION
    -0.69
    wayat
    -0.67
    يكل
    -0.64
    リンク
    -0.63
     EXTENSION
    -0.63
    york
    -0.62
     Serializable
    -0.61
    extension
    -0.60
     extensión
    -0.60
    POSITIVE LOGITS
    cloudfront
    0.71
     Ashland
    0.68
     piec
    0.68
     परि
    0.66
    IntegerField
    0.66
    lict
    0.65
     изу
    0.64
     cb
    0.64
    sihkan
    0.64
     introduces
    0.63
    Activations Density 0.087%

    No Known Activations