© 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. 101273
    Prev
    Next
    INDEX
    Explanations

    lists containing technical terms

    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
    ヮ
    0.52
     perished
    0.45
     হইতেই
    0.44
     file
    0.41
    と思います
    0.41
    [,,"
    0.41
     cleaved
    0.41
    casian
    0.40
    れます
    0.40
    报错
    0.40
    POSITIVE LOGITS
    Titan
    0.53
     Strength
    0.48
     Propri
    0.46
    MPs
    0.46
    Radar
    0.46
    AKI
    0.45
    Ti
    0.44
     Tanks
    0.44
     棚
    0.44
    വ
    0.44
    Activations Density 0.003%

    No Known Activations