© 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. 85446
    Prev
    Next
    INDEX
    Explanations

    wishes and hypothetical scenarios

    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
    𐐪
    -1.67
    噢
    -1.66
     religiosos
    -1.65
    銥
    -1.55
    횃
    -1.48
     каждой
    -1.47
    嘻嘻
    -1.46
    힛
    -1.45
     sueños
    -1.45
    々木
    -1.45
    POSITIVE LOGITS
     which
    1.86
    </h2>
    1.74
     where
    1.59
     indicate
    1.47
     come
    1.45
    咐
    1.45
    '];?>
    1.43
     when
    1.40
     wichtigsten
    1.39
     itſelf
    1.39
    Activations Density 0.007%

    No Known Activations