© 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. 21195
    Prev
    Next
    INDEX
    Explanations

    Q prompts and code formatting

    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
     are
    -2.36
    ];
    -1.76
     was
    -1.76
     the
    -1.75
    !\
    -1.70
    依然
    -1.67
    ">
    -1.66
    );
    -1.66
    ");
    -1.66
    6
    -1.63
    POSITIVE LOGITS
    砹
    1.76
    豪华
    1.68
    PAIGN
    1.61
     remarqu
    1.61
    苼
    1.52
    鱨
    1.51
     teint
    1.50
    ၜ
    1.49
    blumen
    1.48
     休閒
    1.46
    Activations Density 0.000%

    No Known Activations