© 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. 39652
    Prev
    Next
    INDEX
    Explanations

    pirate flag, pirate radio

    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
    </h2>
    -3.28
    </em>
    -3.16
    \
    -2.97
    1
    -2.91
     \&
    -2.84
     \\
    -2.83
     }
    -2.81
    (
    -2.78
    2
    -2.66
    re
    -2.63
    POSITIVE LOGITS
    ’).
    3.03
    ’)
    2.92
    ’;
    2.77
    ’?
    2.69
    
    2.63
    ’:
    2.58
    "},
    2.52
    鬭
    2.42
    --
    2.42
    趼
    2.39
    Activations Density 0.001%

    No Known Activations