© 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. 10-GEMMASCOPE-RES-131K
    7. 510
    Prev
    Next
    INDEX
    Explanations

    code and conditional logic

    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
    including
    -1.63
     hanno
    -1.40
     inklusive
    -1.37
     MAY
    -1.36
    𝗔
    -1.33
    škin
    -1.28
    قامت
    -1.27
    貊
    -1.27
     “
    -1.27
    虽
    -1.25
    POSITIVE LOGITS
     or
    2.14
     then
    1.68
     so
    1.66
     спросил
    1.53
     Gemü
    1.50
     only
    1.41
     used
    1.38
     vorigen
    1.38
     cercando
    1.38
     asked
    1.37
    Activations Density 0.444%

    No Known Activations