© 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-262K
    7. 241473
    Prev
    Next
    INDEX
    Explanations

    specific names/terms

    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
    umu
    0.71
     jamás
    0.56
    fluent
    0.56
     земля
    0.56
     ছাড়াও
    0.55
    ҙ
    0.54
     مشابه
    0.54
     сражение
    0.54
     একেবারে
    0.53
    accouchement
    0.53
    POSITIVE LOGITS
    THEOREM
    0.64
    Leary
    0.63
    觚
    0.63
     প
    0.59
     subheading
    0.58
     छोटी
    0.57
     Concurrent
    0.57
     Jurgen
    0.57
     Рассмотрим
    0.57
     Monthly
    0.57
    Activations Density 0.000%

    No Known Activations