© 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. 10-GEMMASCOPE-RES-131K
    7. 60038
    Prev
    Next
    INDEX
    Explanations

    XML tags 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_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
    ’
    -2.63
    .”
    -2.61
    </h5>
    -2.33
     */
    -2.08
    ⭓
    -1.98
     obstáculos
    -1.95
    S
    -1.92
    ﮦ
    -1.91
     your
    -1.87
    𐑂
    -1.87
    POSITIVE LOGITS
    8
    2.39
     of
    2.16
     swarms
    1.94
    帑
    1.77
     تقری
    1.77
    
    1.77
    凩
    1.76
    杁
    1.76
     generado
    1.75
    zió
    1.75
    Activations Density 0.138%

    No Known Activations