© 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. 73133
    Prev
    Next
    INDEX
    Explanations

    code snippets and mathematical expressions

    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
    akterysty
    -1.50
     waar
    -1.44
    紘
    -1.41
     andere
    -1.38
    riffen
    -1.38
    лика
    -1.38
    ANTAGE
    -1.38
    ksiyon
    -1.35
    ."
    -1.34
     فهي
    -1.32
    POSITIVE LOGITS
    <i>
    1.96
    The
    1.77
    $
    1.74
    This
    1.66
    </blockquote>
    1.63
     his
    1.62
    </i>
    1.59
     that
    1.55
    淠
    1.53
    That
    1.52
    Activations Density 0.002%

    No Known Activations