© 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. 99523
    Prev
    Next
    INDEX
    Explanations

    Tekken

    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
     scoff
    0.39
    klu
    0.39
     Gust
    0.38
     Festive
    0.38
     gusto
    0.38
     fest
    0.38
     festive
    0.38
     맛
    0.38
     seaf
    0.37
     ashore
    0.37
    POSITIVE LOGITS
    Laser
    0.42
    包含了
    0.39
     Title
    0.38
    Equatable
    0.38
     láser
    0.38
     тера
    0.38
     переза
    0.37
    शुल्क
    0.37
     ہزار
    0.37
    Name
    0.37
    Activations Density 0.000%

    No Known Activations