Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8406
    Prev
    Next
    INDEX
    Explanations

    warm from the oven

    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
    ی
    1.30
    ה
    1.23
    ك
    1.20
    तया
    1.05
    ли
    1.04
     noirs
    1.02
     Pathol
    0.98
     hạng
    0.96
    лни
    0.96
    a
    0.96
    POSITIVE LOGITS
    ধ্বনি
    0.98
    蓼
    0.93
    ште
    0.92
    uders
    0.91
    மிக
    0.91
    itudes
    0.91
    فور
    0.91
    hel
    0.90
    ato
    0.88
     SafeArea
    0.88
    Activations Density 0.025%

    No Known Activations