© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178300
    Prev
    Next
    INDEX
    Explanations

    via applications

    np_acts-logits-general · gemini-2.5-flash-lite

    feeling distressed or helpless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     /
    0.50
     APPEND
    0.46
     triples
    0.46
     Y
    0.46
     Website
    0.45
     informing
    0.45
     wpt
    0.44
     affine
    0.44
     জানার
    0.44
     afford
    0.44
    POSITIVE LOGITS
    紊
    0.48
    斯
    0.48
    鼾
    0.47
    贲
    0.47
    军
    0.46
    斯特
    0.44
    禽
    0.44
    تها
    0.43
    userName
    0.43
    ева
    0.43
    Activations Density 0.001%

    No Known Activations