© 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. 73873
    Prev
    Next
    INDEX
    Explanations

    RDF, Rama, SWF, HDF

    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
    辚
    -3.00
    );
    -2.86
     '>=
    -2.47
     "",
    -2.41
    IANGLES
    -2.33
    尨
    -2.25
     maceta
    -2.22
    鉏
    -2.16
    ).
    -2.14
    
    -2.14
    POSITIVE LOGITS
     используются
    2.44
     начинают
    2.36
    的一个
    2.27
    rdf
    2.23
     Where
    2.13
    ↵↵
    2.13
     commonplace
    2.11
    𝓑
    2.09
     используют
    2.03
     
    2.03
    Activations Density 0.002%

    No Known Activations