© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 532
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_65k_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
    awatts
    0.32
     someplace
    0.30
    বার্ট
    0.30
    ヌ
    0.30
    यॉर्क
    0.29
    Hepinize
    0.29
     ined
    0.29
    InnerText
    0.28
     ءَ
    0.28
    cię
    0.28
    POSITIVE LOGITS
     these
    0.35
     These
    0.33
    these
    0.33
    These
    0.32
     Key
    0.32
    Important
    0.31
    =>
    0.30
    https
    0.30
     PDF
    0.30
    In
    0.29
    Activations Density 0.271%

    No Known Activations