Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 240959
    Prev
    Next
    INDEX
    Explanations

    technical and game terms

    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
     इसी
    0.61
    чин
    0.59
    дова
    0.59
    мар
    0.57
    netty
    0.56
    缨
    0.56
    派出
    0.55
    丞
    0.53
     Сим
    0.52
    taining
    0.50
    POSITIVE LOGITS
     lorem
    0.75
     Aguilar
    0.63
     அவற்றில்
    0.62
     degli
    0.61
     anymore
    0.61
     più
    0.59
     Intents
    0.59
     delle
    0.57
     Lorem
    0.57
     সেগুলি
    0.57
    Activations Density 0.001%

    No Known Activations