© 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. 66589
    Prev
    Next
    INDEX
    Explanations

    locations after 'in'

    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
     certain
    -1.20
    holdings
    -1.16
    了不少
    -1.15
    swire
    -1.13
     ($("#
    -1.11
    chestra
    -1.11
    (!(
    -1.10
    ुष
    -1.10
    
    -1.09
     rotación
    -1.09
    POSITIVE LOGITS
     in
    1.80
     on
    1.39
     Usually
    1.23
     However
    1.23
     of
    1.21
     Although
    1.20
     Normally
    1.10
     near
    1.09
     Despite
    1.03
     Often
    1.03
    Activations Density 0.069%

    No Known Activations