© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5336
    Prev
    Next
    INDEX
    Explanations

    bright and related words

    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_38_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
     Weather
    0.36
    lesson
    0.36
    Weather
    0.35
     ilaç
    0.35
    㴦
    0.35
    Presented
    0.34
    ील
    0.34
     WEATHER
    0.34
     apresent
    0.33
    钟
    0.33
    POSITIVE LOGITS
     bright
    0.58
     밝
    0.55
     Bright
    0.55
     terang
    0.54
    Bright
    0.53
    亮
    0.53
     illum
    0.52
    燈
    0.51
    bulb
    0.51
     brightest
    0.50
    Activations Density 0.085%

    No Known Activations