© 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. 43858
    Prev
    Next
    INDEX
    Explanations

    bin followed by Salman

    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
    夢想
    -1.86
     exé
    -1.85
    気付
    -1.78
    紅色
    -1.78
    鱟
    -1.77
     bengal
    -1.77
     nepal
    -1.77
     racon
    -1.74
     ベクター
    -1.74
     Smiling
    -1.73
    POSITIVE LOGITS
    ">
    2.09
    ↵
    1.98
     a
    1.95
    </sup>
    1.95
    4
    1.76
    </h4>
    1.70
    2
    1.69
    𝗮
    1.63
    3
    1.61
    ).
    1.58
    Activations Density 0.038%

    No Known Activations