© 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. 241373
    Prev
    Next
    INDEX
    Explanations

    online data transactions

    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
     lut
    0.57
    屬
    0.56
    ಡು
    0.55
     bala
    0.55
     Eggs
    0.54
     banging
    0.54
    襁
    0.54
     Mirrors
    0.53
     فض
    0.53
     fluttering
    0.53
    POSITIVE LOGITS
    ttino
    0.60
     ใหญ่
    0.60
    navigateTo
    0.59
    瑞
    0.57
    writeFile
    0.55
     beforehand
    0.55
     obtenido
    0.55
     raggi
    0.54
    خاذ
    0.54
    癤
    0.54
    Activations Density 0.000%

    No Known Activations