Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 240939
    Prev
    Next
    INDEX
    Explanations

    Current demand

    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
     hué
    0.64
     ନ
    0.64
     kuchh
    0.64
     selam
    0.63
     哦
    0.63
     bero
    0.62
     gua
    0.62
    㡚
    0.62
     punctatis
    0.61
     isot
    0.61
    POSITIVE LOGITS
    about
    0.69
    Button
    0.68
    asInstanceOf
    0.67
    current
    0.62
    alert
    0.61
    arounds
    0.61
    Current
    0.60
    Demand
    0.60
    mic
    0.58
    attuale
    0.58
    Activations Density 0.000%

    No Known Activations