© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 143
    Prev
    Next
    INDEX
    Explanations

    names and sports participants

    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
    そういえば
    -1.30
     them
    -1.25
     our
    -1.23
    どのような
    -1.23
     предотвра
    -1.22
    他說
    -1.20
    さっそく
    -1.20
    他说
    -1.20
     which
    -1.19
     its
    -1.16
    POSITIVE LOGITS
    '
    1.19
    етка
    1.14
    啻
    1.10
    ,
    1.09
    鴣
    1.09
     européens
    1.07
    <>
    1.06
     な
    1.06
    ஂ
    1.04
     africains
    1.02
    Activations Density 0.001%

    No Known Activations