© 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-262K
    7. 8426
    Prev
    Next
    INDEX
    Explanations

    DNA, RNA, protein flow

    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
    |$
    1.95
    azgo
    1.90
    عو
    1.88
    ה
    1.87
    పాటు
    1.84
    prise
    1.84
     countrymen
    1.82
    ্চ
    1.74
     escol
    1.72
    تي
    1.71
    POSITIVE LOGITS
    م
    2.83
    м
    2.54
    ड
    2.35
    ির
    2.31
    ب
    2.25
     misma
    2.15
    ຼ
    2.07
    و
    2.06
    좔
    1.97
    е
    1.95
    Activations Density 0.014%

    No Known Activations