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. 4963
    Prev
    Next
    INDEX
    Explanations

    emoticons like :D and :3

    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
     EtOAc
    0.42
     RtlOverlay
    0.40
     XGB
    0.40
     الجدول
    0.39
     Tarifleri
    0.39
    㺪
    0.39
     чемпионаты
    0.38
    UARY
    0.37
    Ṛ
    0.37
    Biografia
    0.36
    POSITIVE LOGITS
     laugh
    0.58
     grin
    0.58
    grin
    0.58
    w
    0.58
    wink
    0.55
    laugh
    0.55
     wink
    0.55
     smile
    0.54
     smiling
    0.54
     laughing
    0.54
    Activations Density 0.001%

    No Known Activations