© 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-262K
    7. 6778
    Prev
    Next
    INDEX
    Explanations

    split text or string

    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_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
     acquistare
    1.27
    뢰
    1.27
     achats
    1.24
    یر
    1.22
    ğı
    1.22
     adet
    1.22
    െയി
    1.22
     būt
    1.22
    人的
    1.20
     comportamenti
    1.20
    POSITIVE LOGITS
    cours
    1.54
    ال
    1.40
    ف
    1.39
    го
    1.37
    ب
    1.37
    د
    1.32
    dır
    1.30
    ﺹ
    1.30
    c
    1.29
     Securities
    1.23
    Activations Density 0.017%

    No Known Activations