© 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. 71264
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax

    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
    第一章
    -1.98
    Nå
    -1.86
    牁
    -1.82
    tku
    -1.75
    här
    -1.70
     그녀
    -1.68
     sentada
    -1.67
    denk
    -1.64
    März
    -1.63
     navide
    -1.61
    POSITIVE LOGITS
    s
    2.50
    ce
    2.11
    k
    2.06
    is
    2.05
    es
    2.05
    en
    1.95
    no
    1.90
    us
    1.88
    ia
    1.84
    re
    1.79
    Activations Density 0.004%

    No Known Activations