© 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. 15109
    Prev
    Next
    INDEX
    Explanations

    suggested

    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
     বিশিষ্ট
    0.55
    وقال
    0.53
     оригина
    0.53
     húmed
    0.53
    Sheets
    0.52
     "-----
    0.52
     promin
    0.52
     PRES
    0.52
    dumbbell
    0.52
     기
    0.51
    POSITIVE LOGITS
    进一步
    0.56
     ऊपरी
    0.56
     Accept
    0.55
    accept
    0.55
     Citation
    0.55
     akzept
    0.54
    امد
    0.53
     塩
    0.53
    값
    0.53
     fewest
    0.52
    Activations Density 0.001%

    No Known Activations