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. 47287
    Prev
    Next
    INDEX
    Explanations

    Java regex Matcher

    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
    adays
    1.81
    ns
    1.64
    وأ
    1.59
    \}$,
    1.59
    \}$.
    1.58
    time
    1.53
     anz
    1.44
    neho
    1.44
    transpose
    1.42
     crusher
    1.41
    POSITIVE LOGITS
    ה
    1.90
    𝑑
    1.88
     البته
    1.83
    ﺩ
    1.80
    こちら
    1.78
    𝑇
    1.77
    TER
    1.75
    ن
    1.73
    ار
    1.70
    a
    1.67
    Activations Density 0.000%

    No Known Activations