© 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-TRANSCODER-262K
    7. 164694
    Prev
    Next
    INDEX
    Explanations

    thai politeness markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    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
     |-
    0.44
    arke
    0.43
     Lif
    0.41
    ıll
    0.41
     Comparing
    0.40
     தேர்
    0.40
    栩
    0.40
    improved
    0.40
    ark
    0.39
    $-
    0.39
    POSITIVE LOGITS
     lips
    0.43
     dampen
    0.42
     hamburgers
    0.41
     consist
    0.40
     lockdowns
    0.39
     padlock
    0.39
     burnout
    0.39
     dries
    0.39
     yawning
    0.39
     lip
    0.38
    Activations Density 0.001%

    No Known Activations