© 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. 92415
    Prev
    Next
    INDEX
    Explanations

    darkness, depth, moral, processing

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

    classifying adjectives and superlatives

    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
     六
    0.49
     unir
    0.48
    始めた
    0.48
    箏
    0.48
    塁
    0.46
    дын
    0.45
    었습니다
    0.45
    に出
    0.44
    ETT
    0.43
    ễ
    0.43
    POSITIVE LOGITS
     darkness
    0.63
    ki
    0.53
    riss
    0.53
    im
    0.52
    ab
    0.51
    ling
    0.50
    ris
    0.50
    ima
    0.49
    rish
    0.48
     خلق
    0.47
    Activations Density 0.000%

    No Known Activations