© 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. 67668
    Prev
    Next
    INDEX
    Explanations

    St. followed by a name

    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
    </strong>
    -3.11
    </h3>
    -2.44
     buscando
    -1.99
    年来
    -1.98
    
    -1.88
    量が
    -1.88
     utilizadas
    -1.86
    —“
    -1.83
     beneficiario
    -1.80
     derzeit
    -1.78
    POSITIVE LOGITS
    .''
    2.28
    鲔
    1.92
    "
    1.92
    ');
    
    1.91
    </b>
    1.84
    ');
    1.84
    땃
    1.82
     '';
    1.70
    庒
    1.70
     esetben
    1.69
    Activations Density 0.009%

    No Known Activations