© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6485
    Prev
    Next
    INDEX
    Explanations

    identifiers and structure definitions

    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_31_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
     प्रश्‍
    0.38
    <unused274>
    0.36
     wszyscy
    0.36
    archiwizowane
    0.33
     நிச்சயம்
    0.32
     océano
    0.31
    ผ่าน
    0.31
     ragazzo
    0.31
     increí
    0.31
    частли
    0.31
    POSITIVE LOGITS
    0
    0.39
    1
    0.38
    _
    0.35
     created
    0.35
    ._
    0.35
     unary
    0.35
     components
    0.34
    Table
    0.33
     armor
    0.33
     generated
    0.32
    Activations Density 0.012%

    No Known Activations