© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11450
    Prev
    Next
    INDEX
    Explanations

    electron occupation numbers

    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
    nitt
    -1.18
     design
    -1.16
    val
    -1.13
    ?
    -1.12
    prepareStatement
    -1.08
     percent
    -1.05
     ⓒ
    -1.05
     layout
    -1.05
    el
    -1.05
     results
    -1.05
    POSITIVE LOGITS
    Poh
    1.33
    ♪♪
    1.17
    Aç
    1.15
    Koordin
    1.13
    Daha
    1.11
    ıkları
    1.11
    )։
    1.09
    ผม
    1.07
    ρούν
    1.07
     vagyok
    1.06
    Activations Density 0.003%

    No Known Activations