© 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. 241500
    Prev
    Next
    INDEX
    Explanations

    software libraries, tools

    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
     রাশি
    0.66
     quels
    0.60
     计算
    0.55
     vue
    0.55
     作
    0.54
    hope
    0.54
     pris
    0.53
    雔
    0.53
    staw
    0.52
    IPTS
    0.52
    POSITIVE LOGITS
     genitalia
    0.63
     Walden
    0.62
     XIX
    0.61
     genitals
    0.60
     воздуха
    0.60
     экстра
    0.59
    เร
    0.57
     marketplaces
    0.56
     аре
    0.55
     నమోదు
    0.55
    Activations Density 0.000%

    No Known Activations