© 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. 45020
    Prev
    Next
    INDEX
    Explanations

    volume and fraction

    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
     dapatkan
    -2.31
    
    -2.16
     responsabile
    -2.14
    
    -2.14
     burch
    -2.13
     hemd
    -2.11
    
    -2.11
     daer
    -2.09
     nemico
    -2.06
    瘊
    -2.05
    POSITIVE LOGITS
    </strong>
    2.25
    𐐪
    2.19
     страны
    2.19
    <bos>
    2.09
    軼
    2.09
     tetapi
    2.03
     OGSÅ
    2.02
    volume
    1.99
    瀏
    1.96
     nebo
    1.94
    Activations Density 0.020%

    No Known Activations