© 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. 45089
    Prev
    Next
    INDEX
    Explanations

    TeX, Texas, tex.sx

    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
    .”
    -3.06
    '
    -2.98
    ).
    -2.95
    ↵↵
    -2.56
    them
    -2.44
    }
    -2.34
    炁
    -2.33
     ―
    -2.30
     besondere
    -2.20
     facets
    -2.20
    POSITIVE LOGITS
    tex
    2.86
    er
    2.73
    孥
    2.69
     όταν
    2.67
    
    2.63
    癀
    2.59
    鉭
    2.59
    𓁹
    2.50
    떳
    2.48
    ⤿
    2.45
    Activations Density 0.003%

    No Known Activations