© 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. 10-GEMMASCOPE-RES-131K
    7. 102302
    Prev
    Next
    INDEX
    Explanations

    code separators and keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    sequences of dashes used as visual separators or borders in text formatting.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    zelfde
    -3.16
    寕
    -2.77
    囖
    -2.73
    سجيل
    -2.70
     verschil
    -2.63
    
    -2.63
    咴
    -2.59
    聍
    -2.55
    scarpe
    -2.53
     間取り
    -2.53
    POSITIVE LOGITS
    1
    3.92
    en
    3.63
    la
    3.59
    d
    3.47
    to
    3.39
    (
    3.31
    2
    3.17
    el
    3.11
    s
    3.05
    as
    3.02
    Activations Density 0.001%

    No Known Activations