© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20209
    Prev
    Next
    INDEX
    Explanations

    code structures `{ ( : /` followed by keywords

    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
    </h4>
    -2.36
     also
    -1.92
     favoritas
    -1.76
    </h2>
    -1.71
    鄖
    -1.60
    うまく
    -1.56
     $^{\
    -1.55
     ocupado
    -1.54
    at
    -1.50
     pocit
    -1.46
    POSITIVE LOGITS
    :
    1.84
     thwarted
    1.82
     });
    
    1.80
    出来ます
    1.70
    </i>
    1.68
     =>
    
    1.67
    ’.
    1.66
    /).
    1.60
    tät
    1.56
    .’
    1.55
    Activations Density 0.019%

    No Known Activations