© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11919
    Prev
    Next
    INDEX
    Explanations

    if possible

    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
    </h5>
    -2.39
     to
    -2.36
    </b>
    -2.31
    </h6>
    -1.91
    +}$
    -1.76
    :
    
    -1.75
    などを
    -1.75
     of
    -1.75
    </td>
    -1.70
    );
    
    -1.70
    POSITIVE LOGITS
    .
    2.42
     remainder
    1.83
    Because
    1.73
     first
    1.72
    就會
    1.71
    ꒥
    1.70
     required
    1.70
     would
    1.67
     one
    1.67
     This
    1.59
    Activations Density 0.019%

    No Known Activations