© 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. 10-GEMMASCOPE-RES-131K
    4. 565
    Prev
    Next
    INDEX
    Explanations

    things being available

    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
     the
    -1.57
     disparate
    -1.48
     znacznie
    -1.46
    ffiti
    -1.42
     seeming
    -1.41
     bezpośrednio
    -1.37
    السلام
    -1.35
     needing
    -1.32
    معلومات
    -1.32
     ↓
    -1.30
    POSITIVE LOGITS
     cerámica
    1.67
     but
    1.60
    ⽆
    1.55
     wers
    1.51
     pokud
    1.49
     to
    1.46
     ?
    1.46
     nếu
    1.40
    ?’
    1.38
     republiky
    1.37
    Activations Density 0.021%

    No Known Activations