© 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. 10-GEMMASCOPE-RES-131K
    7. 128667
    Prev
    Next
    INDEX
    Explanations

    code punctuation prefixes

    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_10/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
     Dinas
    -1.88
    </em>
    -1.84
     gewi
    -1.80
     ་
    -1.70
    qai
    -1.69
    裢
    -1.64
    </h2>
    -1.64
     praticamente
    -1.63
    鲩
    -1.63
    </h3>
    -1.62
    POSITIVE LOGITS
    4
    2.06
    2
    1.93
    1
    1.73
    3
    1.67
     still
    1.67
    5
    1.64
     has
    1.55
     supremely
    1.53
     in
    1.52
    0
    1.52
    Activations Density 0.308%

    No Known Activations