© 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. 108193
    Prev
    Next
    INDEX
    Explanations

    filling up posts

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

    annuity and groups

    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
     Вол
    0.51
    юр
    0.47
     Фор
    0.46
     Grounds
    0.46
     Cyborg
    0.46
     Polymer
    0.45
     Koval
    0.45
     활
    0.45
     коюмдары
    0.45
     Chúng
    0.45
    POSITIVE LOGITS
    面の
    0.45
     ascribe
    0.45
    当時
    0.44
     ibid
    0.44
     przyp
    0.43
     faker
    0.43
    と思いますが
    0.42
     xray
    0.42
    顔
    0.42
    迷惑
    0.42
    Activations Density 0.002%

    No Known Activations