© 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. 15322
    Prev
    Next
    INDEX
    Explanations

    service or action modifiers

    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
     for
    -1.87
     his
    -1.71
     us
    -1.65
     ДЛЯ
    -1.47
    先是
    -1.40
     instead
    -1.38
    -
    -1.38
    諭
    -1.37
     zamiast
    -1.35
     diferentes
    -1.34
    POSITIVE LOGITS
     occupa
    1.55
    笮
    1.55
    </b>
    1.52
     أيضًا
    1.50
     rapor
    1.47
     boya
    1.41
     renk
    1.41
     also
    1.40
     proteine
    1.39
     cucina
    1.38
    Activations Density 0.081%

    No Known Activations