© 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. 22-GEMMASCOPE-RES-131K
    7. 72130
    Prev
    Next
    INDEX
    Explanations

    explaining and informing

    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
    elashes
    -0.92
     innerhalb
    -0.91
    素直
    -0.91
     május
    -0.91
    客气
    -0.89
    我已经
    -0.89
    ída
    -0.88
     from
    -0.87
    ($.
    -0.86
    省市镇
    -0.85
    POSITIVE LOGITS
     explain
    1.73
     about
    1.69
     explanation
    1.68
     how
    1.54
     explaining
    1.44
     explained
    1.38
     options
    1.35
     explicar
    1.34
     information
    1.30
     explicó
    1.27
    Activations Density 0.022%

    No Known Activations