© 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. 22-GEMMASCOPE-RES-131K
    7. 15362
    Prev
    Next
    INDEX
    Explanations

    javascript lodash library

    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_22/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
    ➢
    -1.33
     holder
    -1.21
    Arcane
    -1.13
     одежду
    -1.11
    zeigen
    -1.10
    是很
    -1.10
    aimana
    -1.09
     aven
    -1.09
     juz
    -1.09
    Monument
    -1.08
    POSITIVE LOGITS
     not
    1.29
     entire
    1.27
     extensively
    1.20
     aggressively
    1.20
    ₨
    1.11
     całkow
    1.09
     millón
    1.04
    Btn
    1.03
     intensively
    1.00
    reros
    0.98
    Activations Density 0.017%

    No Known Activations