© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10868
    Prev
    Next
    INDEX
    Explanations

    feeling exhausted or overwhelmed

    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_40_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
    pickMenu
    0.41
     ocupa
    0.39
    occup
    0.35
     occupying
    0.35
    揊
    0.35
    ObjData
    0.34
    ্মান
    0.34
    дые
    0.34
    镛
    0.34
    ꯔ
    0.33
    POSITIVE LOGITS
     feeling
    1.39
     Feeling
    1.30
    Feeling
    1.28
    feeling
    1.13
     sentirse
    1.01
     feels
    1.00
     чув
    0.99
    feels
    0.97
     feel
    0.97
     FEEL
    0.95
    Activations Density 0.114%

    No Known Activations