© 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. 7118
    Prev
    Next
    INDEX
    Explanations

    quality or strength

    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
    ⬈
    -1.95
     ``
    -1.90
     Our
    -1.88
    皷
    -1.87
     Там
    -1.85
    勦
    -1.85
     Brings
    -1.83
     nuove
    -1.83
    pieza
    -1.80
    increased
    -1.79
    POSITIVE LOGITS
    {~
    2.19
    );
    2.03
    Even
    1.84
    .”
    1.83
    Only
    1.82
    };
    1.79
    Just
    1.79
    or
    1.77
    是一
    1.76
    and
    1.75
    Activations Density 0.008%

    No Known Activations