© 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. 67755
    Prev
    Next
    INDEX
    Explanations

    Interaction of

    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
     (
    -1.49
     from
    -1.13
    したので
    -1.05
     søndag
    -0.95
    一会儿
    -0.93
     mitään
    -0.93
     in
    -0.91
     Proof
    -0.88
    场合
    -0.86
    собы
    -0.85
    POSITIVE LOGITS
     &,
    1.07
     eventuell
    1.06
     dibat
    1.05
    Nº
    1.05
     appuntamento
    1.03
    Instead
    1.03
     brachten
    1.03
     singola
    1.00
    雰囲
    0.99
     jezt
    0.99
    Activations Density 0.001%

    No Known Activations