© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44591
    Prev
    Next
    INDEX
    Explanations

    comparisons between two entities

    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
    }}$.
    -1.37
    ämme
    -1.27
    cesis
    -1.24
     refugi
    -1.22
    );
    
    -1.21
    >();
    -1.19
     the
    -1.18
    '])){
    
    -1.15
    ),
    -1.14
    拢
    -1.13
    POSITIVE LOGITS
    7
    1.54
    8
    1.48
    Also
    1.48
    These
    1.37
    Some
    1.35
    Most
    1.31
    Not
    1.30
    Often
    1.29
    Sometimes
    1.29
    Where
    1.29
    Activations Density 0.043%

    No Known Activations