© 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. 241504
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    beyblade
    0.57
    ㅀ
    0.51
    ̖
    0.50
     asesinato
    0.50
     ses
    0.50
     azo
    0.50
    鸽
    0.50
    yect
    0.50
    ؘ
    0.49
     তখনকার
    0.49
    POSITIVE LOGITS
     મહ
    0.55
     మహా
    0.55
    স্থার
    0.55
    novation
    0.53
    дера
    0.53
     θέ
    0.53
    DAL
    0.52
     न्यूनतम
    0.52
     дело
    0.51
     horrend
    0.50
    Activations Density 0.002%

    No Known Activations