© 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. 14980
    Prev
    Next
    INDEX
    Explanations

    countries

    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
     Certaines
    0.60
    而在
    0.59
     যৌগ
    0.56
    而不
    0.54
    塊
    0.54
     viac
    0.53
     Nhiều
    0.53
    getR
    0.51
    芍
    0.51
    zuki
    0.51
    POSITIVE LOGITS
     Hungary
    0.59
     Mauritius
    0.58
     Finland
    0.57
     honest
    0.55
     Ireland
    0.55
     Spain
    0.54
     hassle
    0.54
     affiliation
    0.54
     Execution
    0.53
     France
    0.52
    Activations Density 0.000%

    No Known Activations