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. 8193
    Prev
    Next
    INDEX
    Explanations

    whip or whipped cream

    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
    autres
    1.72
    bbs
    1.68
    aren
    1.62
    esi
    1.58
    ли
    1.54
    gp
    1.52
    éléments
    1.52
    e
    1.50
    ا
    1.50
    sell
    1.49
    POSITIVE LOGITS
    soever
    2.34
    서
    2.13
    นี้
    1.77
    ก็ตาม
    1.76
     말고
    1.70
     Fractions
    1.67
    もっと
    1.63
    โมง
    1.63
     tắt
    1.59
    ጥር
    1.58
    Activations Density 0.004%

    No Known Activations