© 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. 99921
    Prev
    Next
    INDEX
    Explanations

    tokens defined with parentheses

    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
     and
    -3.20
     -
    -2.78
    ↵
    -2.78
    </h4>
    -2.75
     had
    -2.64
     If
    -2.59
     как
    -2.58
     Surprisingly
    -2.58
     ---
    -2.50
     from
    -2.48
    POSITIVE LOGITS
    
    3.13
    Ꮷ
    2.81
    ৢ
    2.75
     haupts
    2.69
    鲞
    2.69
    蘩
    2.67
    訁
    2.64
    矬
    2.64
     contín
    2.63
    
    2.61
    Activations Density 0.010%

    No Known Activations