© 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. 15092
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    ルダー
    0.57
     Willow
    0.52
    的不同
    0.50
    árd
    0.50
     受
    0.49
    鄂
    0.49
     vented
    0.48
     Fork
    0.47
     απα
    0.47
     назна
    0.46
    POSITIVE LOGITS
     Dan
    0.63
    acters
    0.62
     berwarna
    0.60
    ওর
    0.59
    Discover
    0.57
     kaca
    0.56
     menutup
    0.56
     logout
    0.55
     voce
    0.55
    閉
    0.55
    Activations Density 0.000%

    No Known Activations