© 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. 241431
    Prev
    Next
    INDEX
    Explanations

    what are questions

    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
     மஹ
    0.71
     their
    0.66
     ARE
    0.64
    ৃত্য
    0.62
    れば
    0.62
     plumbing
    0.62
     Mahm
    0.61
     ধ
    0.60
     Rwanda
    0.60
    ब्बे
    0.60
    POSITIVE LOGITS
    Seems
    0.76
    seems
    0.71
    ется
    0.70
     seems
    0.69
     represents
    0.66
    тным
    0.64
     상황
    0.63
    гим
    0.62
     follows
    0.62
    方面
    0.62
    Activations Density 0.002%

    No Known Activations