© 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-65K
    7. 15016
    Prev
    Next
    INDEX
    Explanations

    temporary unique identifiers

    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_65k_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
     कं
    0.59
    ポイント
    0.59
    точка
    0.57
     Kab
    0.55
     Hota
    0.55
    ⴷ
    0.55
    ெல்லி
    0.53
    
    0.53
     Legisl
    0.53
     ポイント
    0.52
    POSITIVE LOGITS
     tmp
    0.60
     udp
    0.56
     temporarily
    0.55
    图形
    0.55
     typ
    0.54
     backup
    0.54
     etsy
    0.54
     temporary
    0.54
    Tmp
    0.53
     backups
    0.53
    Activations Density 0.000%

    No Known Activations