© 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. 67115
    Prev
    Next
    INDEX
    Explanations

    add a touch

    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
     for
    -1.77
    翻訳
    -1.76
    𓋼
    -1.63
     blessés
    -1.61
     télécharge
    -1.59
    悲伤
    -1.58
    女性の
    -1.55
    兒子
    -1.48
    睒
    -1.47
    鬭
    -1.45
    POSITIVE LOGITS
    </sup>
    1.80
     ؛
    1.77
    5
    1.73
     setImage
    1.69
    henswürdigkeiten
    1.67
    y
    1.67
    1
    1.63
     напом
    1.63
     )
    1.61
    '.
    1.60
    Activations Density 0.007%

    No Known Activations