© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47814
    Prev
    Next
    INDEX
    Explanations

    quoted strings or identifiers

    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
    ”),
    -1.77
    ”,
    -1.64
    );
    -1.49
     it
    -1.46
    ),
    -1.46
    ”).
    -1.37
    »;
    -1.35
    "],
    -1.35
     at
    -1.34
     by
    -1.34
    POSITIVE LOGITS
     overpowering
    1.64
    핌
    1.47
    another
    1.44
     extrêmement
    1.42
     takiego
    1.37
    begins
    1.37
    ПИ
    1.30
    Nevertheless
    1.30
    {
    1.30
    Another
    1.28
    Activations Density 0.022%

    No Known Activations