© 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. 15083
    Prev
    Next
    INDEX
    Explanations

    Romanian context

    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
    Printing
    0.63
    Xia
    0.63
    情人
    0.61
     cuc
    0.60
    Mos
    0.59
    Mate
    0.58
     Elevated
    0.58
    忙
    0.57
    Manufacturing
    0.57
    QRCode
    0.57
    POSITIVE LOGITS
     ses
    0.68
     terg
    0.63
     مداخل
    0.59
     ramb
    0.59
     ach
    0.59
     analy
    0.57
     AN
    0.57
     KE
    0.57
     ke
    0.56
     sessions
    0.56
    Activations Density 0.001%

    No Known Activations