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-65K
    4. 4179
    Prev
    Next
    INDEX
    Explanations

    HTML

    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
     Yama
    0.86
     Larissa
    0.76
    SizePolicy
    0.74
    姶
    0.72
     Yamaha
    0.72
    ヨ
    0.72
     京都
    0.70
     solvers
    0.70
     Yor
    0.70
    銚
    0.69
    POSITIVE LOGITS
     HTML
    4.49
    HTML
    4.44
     html
    4.15
    html
    4.15
    Html
    3.76
     Html
    3.59
    htm
    2.55
     HT
    2.04
    <html>
    1.99
     XHTML
    1.95
    Activations Density 0.447%

    No Known Activations