© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 204727
    Prev
    Next
    INDEX
    Explanations

    impacting speech and swallowing

    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
    কবি
    0.45
    عبير
    0.43
    来自
    0.43
    缜
    0.40
    ʚ
    0.40
    EnglishMarks
    0.40
    Mientras
    0.40
    लग्न
    0.39
    وفيق
    0.39
    сле
    0.39
    POSITIVE LOGITS
     rice
    0.42
     beige
    0.40
    atino
    0.39
    </caption>
    0.38
     gratuitement
    0.37
    東京
    0.37
     marketable
    0.37
     dość
    0.37
     asi
    0.36
     antes
    0.36
    Activations Density 0.001%

    No Known Activations