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. 17-GEMMASCOPE-2-RES-65K
    4. 2013
    Prev
    Next
    INDEX
    Explanations

    foreign names or places

    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_17_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
     leeway
    0.62
     다
    0.58
     seepage
    0.55
     사용
    0.52
    ZIONE
    0.51
     이것
    0.51
     생성
    0.50
     여러
    0.50
     equivari
    0.49
    ه
    0.49
    POSITIVE LOGITS
    ay
    0.63
    în
    0.60
    èn
    0.58
    ani
    0.57
    ják
    0.57
    ène
    0.55
    ínio
    0.54
    ács
    0.53
    île
    0.52
    sa
    0.52
    Activations Density 0.200%

    No Known Activations