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. 9-GEMMASCOPE-2-RES-262K
    4. 7327
    Prev
    Next
    INDEX
    Explanations

    parts of sorts

    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_9_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
    ح
    2.41
    ২০
    2.09
    Eau
    2.03
    buf
    1.95
    sthe
    1.94
    その
    1.91
    €™
    1.90
    ()=>{
    1.89
    ज
    1.88
     salvation
    1.86
    POSITIVE LOGITS
     sorts
    2.11
     видов
    1.98
    Всем
    1.85
     selves
    1.82
     harms
    1.80
    tei
    1.79
     הן
    1.79
    eseen
    1.79
     kinds
    1.78
     phận
    1.73
    Activations Density 0.090%

    No Known Activations