© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1083
    Prev
    Next
    INDEX
    Explanations

    pronouns before verbs and nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    re
    2.36
    u
    2.19
    t
    2.08
    ள்
    1.80
    seiten
    1.79
    ים
    1.78
    lll
    1.77
    एस
    1.75
    ra
    1.73
    すすめ
    1.72
    POSITIVE LOGITS
    ج
    3.19
    सँग
    2.30
    اس
    2.13
     institu
    2.08
    д
    2.00
    ка
    1.96
     Excellency
    1.96
    ה
    1.96
    ங்கிணை
    1.91
    اب
    1.91
    Activations Density 0.312%

    No Known Activations