© 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. 85396
    Prev
    Next
    INDEX
    Explanations

    event names and types

    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
    </strong>
    -1.63
     also
    -1.35
    </h4>
    -1.34
     currently
    -1.34
     vorhandenen
    -1.26
    <em>
    -1.24
     mientras
    -1.21
    =[];
    -1.21
    Also
    -1.19
    すでに
    -1.19
    POSITIVE LOGITS
    phalt
    1.26
    📩
    1.21
    などなど
    1.19
    嚣
    1.17
    mechanism
    1.17
    meetings
    1.16
    vų
    1.15
    purposes
    1.13
    takings
    1.12
    iculture
    1.11
    Activations Density 0.080%

    No Known Activations