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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 1087
    Prev
    Next
    INDEX
    Explanations

    engine and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concedes
    0.76
    zellen
    0.74
    หว่าง
    0.72
     )$
    0.72
     عطا
    0.70
     instantiate
    0.68
     championed
    0.67
     شوید
    0.67
    .(*
    0.67
    ⑮
    0.67
    POSITIVE LOGITS
     engine
    0.73
    Engine
    0.72
    ія
    0.71
    Appl
    0.70
     Engine
    0.69
    ії
    0.69
    end
    0.69
     স্থানীয়
    0.68
    engine
    0.68
     അവർ
    0.66
    Activations Density 0.000%

    No Known Activations