© 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. 20280
    Prev
    Next
    INDEX
    Explanations

    two copies

    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
    ഖ
    0.49
    กว่า
    0.42
     gitar
    0.42
     रेखा
    0.42
     Straw
    0.41
    铨
    0.41
    Straw
    0.40
    aden
    0.40
     പങ്ക
    0.40
    㧔
    0.40
    POSITIVE LOGITS
     error
    0.50
    cinoma
    0.49
    Error
    0.48
     취
    0.47
    민
    0.47
     oyster
    0.47
     предоставля
    0.47
     omit
    0.46
     violent
    0.46
     ক্যা
    0.46
    Activations Density 0.001%

    No Known Activations