© 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-65K
    7. 1060
    Prev
    Next
    INDEX
    Explanations

    specific online informational sources

    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_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
     giddy
    0.24
    listeners
    0.23
    <unused985>
    0.23
     allemaal
    0.23
    妵
    0.23
     tyranny
    0.22
     همه
    0.22
    ManagerState
    0.21
    ブラック
    0.21
     ನಿಮಗೆ
    0.21
    POSITIVE LOGITS
    8
    0.24
    7
    0.24
    
    0.23
     &
    0.21
     del
    0.21
    ﾎ
    0.21
     international
    0.21
     fluv
    0.21
     Deutsches
    0.21
    ौला
    0.21
    Activations Density 0.198%

    No Known Activations