© 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. 87129
    Prev
    Next
    INDEX
    Explanations

    lacked, by, having, have, damage, directly

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

    necessity for depth or understanding

    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
     Sonic
    0.41
    猩
    0.41
     Puzzle
    0.40
     Integer
    0.39
     porcine
    0.39
    鲅
    0.39
    GT
    0.39
    智能
    0.39
    iprofloxacin
    0.39
    𝐦
    0.39
    POSITIVE LOGITS
    nesset
    0.50
    eture
    0.46
    после
    0.46
    edited
    0.46
    answers
    0.45
    knock
    0.44
    atthe
    0.44
    ის
    0.43
    inprogress
    0.43
     केवाईसी
    0.43
    Activations Density 0.001%

    No Known Activations