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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41234
    Prev
    Next
    INDEX
    Explanations

    Hugging Face Hub models

    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_65k_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
     placés
    0.82
     placé
    0.78
    Beverungen
    0.74
    <end_of_turn>
    0.73
    اهر
    0.71
    <unused90>
    0.71
    မျက်
    0.71
    ស្ថានភាព
    0.71
    ្រី
    0.70
    hiq
    0.70
    POSITIVE LOGITS
     engine
    0.87
     Engine
    0.84
    ない
    0.81
     minus
    0.76
     +
    0.73
    Arena
    0.69
     ENGINE
    0.69
     इंजन
    0.68
     engines
    0.68
    エンジン
    0.66
    Activations Density 0.003%

    No Known Activations