© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 3857
    Prev
    Next
    INDEX
    Explanations

    printing epoch and iteration counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ან
    0.38
     वरीय
    0.36
     मर्ज
    0.35
     projectile
    0.35
     attic
    0.35
    ꯠ
    0.34
    見る
    0.34
    MapView
    0.34
    ราม
    0.34
    囔
    0.34
    POSITIVE LOGITS
    oha
    0.38
    ៩
    0.36
    ᱙
    0.36
    rectionType
    0.35
     Triumph
    0.35
     Ninth
    0.34
    第
    0.34
    )++;
    0.34
     ninth
    0.33
     polyg
    0.33
    Activations Density 0.001%

    No Known Activations