© 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. 15025
    Prev
    Next
    INDEX
    Explanations

    Persian

    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
     документи
    0.55
     фон
    0.55
     senhor
    0.54
     dikdört
    0.53
     ouvir
    0.52
     admet
    0.52
    실
    0.51
     chis
    0.50
     eşit
    0.49
     পার্
    0.49
    POSITIVE LOGITS
     Eth
    0.60
    امه
    0.59
    䔬
    0.59
     ETH
    0.55
     Cambio
    0.55
    背
    0.55
     背
    0.55
    橡胶
    0.55
     जुनून
    0.55
     Selection
    0.54
    Activations Density 0.001%

    No Known Activations