© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241364
    Prev
    Next
    INDEX
    Explanations

    specific items/entities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dobl
    0.54
     ಪಿ
    0.52
    サッカー
    0.51
    ოში
    0.50
     extender
    0.50
     hemen
    0.49
     ഒ
    0.49
     asegur
    0.49
    живання
    0.48
    沖
    0.48
    POSITIVE LOGITS
     ETFs
    0.60
    മി
    0.56
     新品
    0.55
     Gespr
    0.54
     glimpses
    0.54
    
    0.54
    emoration
    0.53
    ⿻
    0.53
     gesprek
    0.53
     conversations
    0.52
    Activations Density 0.001%

    No Known Activations