© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9919
    Prev
    Next
    INDEX
    Explanations

    darkness

    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_13_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
    '
    0.38
     on
    0.37
     roadblocks
    0.36
     tangents
    0.35
     rash
    0.33
     uphe
    0.33
     ot
    0.32
     obstacles
    0.31
     facets
    0.31
     sensibilities
    0.31
    POSITIVE LOGITS
     darkness
    0.51
    黑暗
    0.50
     Darkness
    0.49
    闇
    0.48
    DARK
    0.44
    dark
    0.43
    Dark
    0.43
    ダーク
    0.41
    黑
    0.40
    ريقيا
    0.40
    Activations Density 0.042%

    No Known Activations