© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 109547
    Prev
    Next
    INDEX
    Explanations

    numbered definitions and explanations

    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
    ink
    0.43
    ind
    0.42
    ндар
    0.40
    ള്ള
    0.40
    <start_of_turn>
    0.38
    dueDate
    0.37
     egen
    0.37
    aff
    0.36
    rezz
    0.36
    स्वर
    0.36
    POSITIVE LOGITS
     comest
    0.37
     chromat
    0.36
    オブジェクト
    0.36
    গুলি
    0.35
    ดื่ม
    0.35
     mansion
    0.34
    ษย์
    0.34
     transactional
    0.34
    والي
    0.34
    殉
    0.34
    Activations Density 0.006%

    No Known Activations