© 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. 241454
    Prev
    Next
    INDEX
    Explanations

    plan for today

    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
    他和
    0.84
    roduction
    0.64
    gtrsim
    0.61
    导致
    0.59
    ørt
    0.59
    his
    0.58
    jskiej
    0.58
    
    0.57
    followed
    0.56
    rasında
    0.55
    POSITIVE LOGITS
     today
    0.79
     сегодня
    0.72
     heute
    0.71
     positively
    0.70
     Muay
    0.70
     오늘의
    0.69
    今日
    0.68
     sill
    0.66
     сьогодні
    0.66
     todays
    0.66
    Activations Density 0.000%

    No Known Activations