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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11530
    Prev
    Next
    INDEX
    Explanations

    sets of words or symbols

    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
     "
    -1.36
    蟥
    -1.36
     nebst
    -1.34
     into
    -1.34
    mogen
    -1.26
    pherds
    -1.22
     tumultuous
    -1.21
     ''
    -1.19
    tsd
    -1.19
    cún
    -1.18
    POSITIVE LOGITS
    مقدمه
    1.38
    塤
    1.38
     umane
    1.35
    焢
    1.34
    Hasil
    1.32
    Makanan
    1.29
    Пример
    1.28
     probleme
    1.28
    تمر
    1.27
     itſelf
    1.26
    Activations Density 0.000%

    No Known Activations