© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15300
    Prev
    Next
    INDEX
    Explanations

    context and information

    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
    Olivia
    0.59
    फेल
    0.57
     фигур
    0.56
    offsetTop
    0.56
    antique
    0.55
    amist
    0.55
    vintage
    0.54
    킷
    0.54
    Mam
    0.54
    ANNOT
    0.54
    POSITIVE LOGITS
     ر
    0.64
     derm
    0.61
     blitt
    0.61
     র
    0.60
     gh
    0.58
     chr
    0.58
     rc
    0.56
     ਘ
    0.56
     R
    0.56
     hs
    0.56
    Activations Density 0.000%

    No Known Activations