© 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. 14916
    Prev
    Next
    INDEX
    Explanations

    rules and obedience

    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
    $&$
    0.57
    ایات
    0.56
    toMatch
    0.55
    Atlas
    0.55
    emás
    0.55
    adhat
    0.55
    CTest
    0.54
    $&$-
    0.53
    Mesh
    0.52
    سات
    0.52
    POSITIVE LOGITS
     wattage
    0.61
     ram
    0.61
     power
    0.60
     힘
    0.59
    োধনী
    0.59
     MEGA
    0.59
    冲突
    0.58
     비율
    0.58
     ხ
    0.57
     قوة
    0.57
    Activations Density 0.000%

    No Known Activations