© 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. 241530
    Prev
    Next
    INDEX
    Explanations

    and

    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
    astom
    0.63
     আমরা
    0.60
    スマホ
    0.60
    唛
    0.60
    鵃
    0.60
     موم
    0.59
     ATO
    0.59
    audioType
    0.57
     լ
    0.57
    コレクション
    0.55
    POSITIVE LOGITS
    үү
    0.70
     revise
    0.60
     matched
    0.59
     revising
    0.57
     refurbished
    0.57
     stimulate
    0.57
     sebagian
    0.57
     establish
    0.56
    matched
    0.55
    ดำ
    0.54
    Activations Density 0.000%

    No Known Activations