© 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. 67522
    Prev
    Next
    INDEX
    Explanations

    shortages and problems

    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
    琹
    -3.30
     humeur
    -2.98
    蹋
    -2.92
    )
    -2.89
    鬭
    -2.88
    ︕
    -2.84
    慙
    -2.78
     cittadino
    -2.72
     économie
    -2.67
     efficacité
    -2.67
    POSITIVE LOGITS
    ).
    3.27
    </h4>
    2.95
    ){
    2.61
    );
    2.59
    ↵↵↵↵
    2.58
    所以我
    2.47
     terwijl
    2.39
    </b>
    2.34
    ”,
    2.33
    }{
    2.27
    Activations Density 0.008%

    No Known Activations