© 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. 113633
    Prev
    Next
    INDEX
    Explanations

    military rigor or Army officer

    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
    <blockquote>
    -1.48
    <
    -1.48
    ");
    -1.41
    This
    -1.41
    ".
    -1.41
    Those
    -1.40
    That
    -1.38
    ."
    -1.37
    ",
    -1.37
    Both
    -1.33
    POSITIVE LOGITS
     you
    1.63
     titolata
    1.48
    tront
    1.44
    푆
    1.44
     別注
    1.42
    柺
    1.41
     your
    1.40
    Ruju
    1.35
    镠
    1.35
     排骨
    1.34
    Activations Density 17.235%

    No Known Activations