Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113
    Prev
    Next
    INDEX
    Explanations

    numbers followed by 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_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
     you
    -1.55
     that
    -1.47
    吞噬
    -1.46
    是一款
    -1.32
     že
    -1.28
     I
    -1.23
    votre
    -1.20
    潜力
    -1.19
    hu
    -1.17
    も多く
    -1.17
    POSITIVE LOGITS
     when
    1.95
     two
    1.61
     after
    1.55
     one
    1.54
     if
    1.46
     out
    1.41
     new
    1.41
     three
    1.41
     but
    1.35
    attaque
    1.35
    Activations Density 0.035%

    No Known Activations