Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8573
    Prev
    Next
    INDEX
    Explanations

    historic preservation and designations

    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
    geom
    -0.81
    crimson
    -0.81
     NSF
    -0.80
    ற்ற
    -0.79
     chaplain
    -0.78
    NSF
    -0.77
     announ
    -0.76
     crecimiento
    -0.76
    GraphicsUnit
    -0.75
     officiating
    -0.74
    POSITIVE LOGITS
     Historic
    1.97
    Historic
    1.96
     historic
    1.91
    historic
    1.69
     истори
    1.44
     Historical
    1.44
     historical
    1.42
    Historical
    1.42
     HISTOR
    1.29
     historischen
    1.29
    Activations Density 0.033%

    No Known Activations