© 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. 72632
    Prev
    Next
    INDEX
    Explanations

    addressing issues and questions

    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
     "
    -3.39
     {
    -2.78
     Hinblick
    -2.77
    亹
    -2.67
     avec
    -2.66
     一
    -2.59
    描写
    -2.59
    水を
    -2.55
    蓠
    -2.50
    ᚔ
    -2.50
    POSITIVE LOGITS
    ープン
    3.63
    衎
    3.34
    煐
    3.17
    𖥦
    3.11
    ஂ
    3.11
     レスト
    2.95
    褡
    2.84
    鏵
    2.83
    鳢
    2.83
    鱘
    2.80
    Activations Density 0.016%

    No Known Activations