© 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. 241376
    Prev
    Next
    INDEX
    Explanations

    rules and social structures

    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
     Олександр
    0.74
     succede
    0.64
    hag
    0.64
     caric
    0.64
    福島
    0.64
    ification
    0.63
    dQ
    0.63
    槻
    0.63
    kangaroo
    0.62
     መሳሪያ
    0.61
    POSITIVE LOGITS
    ым
    0.68
    thel
    0.65
    ரசுக்
    0.63
    товые
    0.62
     Records
    0.59
     reference
    0.57
     rises
    0.57
     Dix
    0.57
    竪
    0.56
     Mackenzie
    0.56
    Activations Density 0.000%

    No Known Activations