© 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. 199732
    Prev
    Next
    INDEX
    Explanations

    Bhutan

    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
    abá
    0.43
    ющимся
    0.42
    ンテージ
    0.40
    cailles
    0.40
    rae
    0.39
     此
    0.38
    此
    0.38
     replaceable
    0.38
     અનુસાર
    0.38
    .$$
    0.37
    POSITIVE LOGITS
     fokus
    0.42
     kanal
    0.41
     kajian
    0.41
     mater
    0.41
     Waiting
    0.40
    ostatic
    0.40
     Gaming
    0.40
     Watching
    0.39
     doct
    0.39
     תי
    0.39
    Activations Density 0.007%

    No Known Activations