© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 62
    Prev
    Next
    INDEX
    Explanations

    urgent or emphatic statements

    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_16k_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
    en
    2.42
    ة
    2.26
    ה
    2.14
    ン
    1.91
    ার
    1.83
    a
    1.74
    enian
    1.73
    い
    1.66
    enol
    1.64
    ت
    1.63
    POSITIVE LOGITS
    ?!?
    1.67
    𝖺
    1.46
    ب
    1.41
    ्स
    1.35
    ்
    1.33
    ج
    1.27
    ast
    1.23
     preceded
    1.23
    ERS
    1.22
    ?!?!
    1.22
    Activations Density 0.464%

    No Known Activations