© 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-262K
    4. 241495
    Prev
    Next
    INDEX
    Explanations

    factual 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_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
    etten
    0.79
    ilen
    0.64
    ř
    0.63
    hes
    0.62
    dH
    0.62
     descansar
    0.61
    ن
    0.60
    ν
    0.60
    attutto
    0.59
    adn
    0.59
    POSITIVE LOGITS
     କରି
    0.74
     Calcula
    0.67
     Bacillus
    0.66
     Seja
    0.65
    睒
    0.64
     blaster
    0.64
     sillon
    0.63
     мала
    0.62
    IsPass
    0.61
     nghiên
    0.61
    Activations Density 0.000%

    No Known Activations