© 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. 241577
    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_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
    勛
    0.65
    ٢
    0.64
     двадцать
    0.63
    ١
    0.63
    ၁
    0.62
    ٦
    0.62
    ствую
    0.61
    oresis
    0.61
     ١
    0.60
    izumab
    0.60
    POSITIVE LOGITS
     direct
    0.62
     elevates
    0.59
     "[
    0.59
    рит
    0.59
     shared
    0.58
     discriminating
    0.58
     Demp
    0.57
     Dyer
    0.56
     Pok
    0.55
     Scarborough
    0.55
    Activations Density 0.000%

    No Known Activations