© 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. 14650
    Prev
    Next
    INDEX
    Explanations

    Sullivan, sulphonate, sulcus

    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
    鈇
    -3.61
    衚
    -3.30
    獁
    -3.20
    衎
    -2.98
    蛩
    -2.91
    皤
    -2.86
    趼
    -2.80
     zů
    -2.78
     verminder
    -2.67
     verkau
    -2.66
    POSITIVE LOGITS
    蓠
    3.89
    en
    3.09
    鲼
    2.70
     --
    2.61
    骉
    2.59
     españoles
    2.56
    螻
    2.56
    茈
    2.45
    های
    2.39
     españolas
    2.38
    Activations Density 0.007%

    No Known Activations