© 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. 39499
    Prev
    Next
    INDEX
    Explanations

    parsing hexadecimal byte values

    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
     после
    -1.09
     xlink
    -1.06
     setelah
    -1.06
    setArguments
    -1.02
    QRect
    -1.02
     BeautifulSoup
    -1.02
    neous
    -1.02
     трубы
    -1.01
     dimiliki
    -1.01
    roids
    -1.01
    POSITIVE LOGITS
    ῖς
    1.05
     retries
    0.95
     právě
    0.95
     lovel
    0.93
     afrontar
    0.92
     obicei
    0.92
     Idiot
    0.90
     Modus
    0.90
    σιμοποι
    0.88
     accompan
    0.88
    Activations Density 0.009%

    No Known Activations