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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1491
    Prev
    Next
    INDEX
    Explanations

    list of attributes and characteristics

    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
     donn
    0.36
    轸
    0.35
     démon
    0.33
     Му
    0.32
    بس
    0.31
    ду
    0.30
    ч
    0.29
     compét
    0.28
     تعالى
    0.28
     $_{\
    0.28
    POSITIVE LOGITS
    /-
    0.46
     extraordinaire
    0.46
     Ham
    0.35
    ที่ดี
    0.33
    mlung
    0.33
    ளுக்காக
    0.33
    Ham
    0.32
     నేపథ్యంలో
    0.32
     ham
    0.32
    上限
    0.32
    Activations Density 0.197%

    No Known Activations