© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69893
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in code

    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
    dzić
    -1.81
    годно
    -1.48
     mengerti
    -1.39
    므
    -1.38
     attacco
    -1.38
     that
    -1.37
     nessun
    -1.37
    ضير
    -1.35
    いっ
    -1.35
     ihren
    -1.35
    POSITIVE LOGITS
    那
    1.44
    </h4>
    1.35
    );
    1.34
     what
    1.34
    我的
    1.31
     seemed
    1.31
    akteur
    1.30
     four
    1.30
     ?>
    1.29
     mostly
    1.27
    Activations Density 0.029%

    No Known Activations