© 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. 861
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units of time

    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
    en
    0.60
    is
    0.47
    faktor
    0.45
    ע
    0.44
    erweise
    0.43
    Ethereum
    0.41
    dır
    0.41
    os
    0.41
    zelfde
    0.41
    User
    0.40
    POSITIVE LOGITS
    να
    0.44
    0.38
    н
    0.38
     первая
    0.37
    ਨ
    0.37
    页面存档备份
    0.37
    2
    0.36
     거의
    0.36
     Beneficial
    0.35
     وتر
    0.35
    Activations Density 1.721%

    No Known Activations