© 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. 92464
    Prev
    Next
    INDEX
    Explanations

    everyone who or future

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

    Post transformation or field generation

    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
     x
    0.46
     قصد
    0.45
     =
    0.44
     q
    0.44
     కూడా
    0.44
     Ξ
    0.43
     광고
    0.42
     נא
    0.42
     Ñ
    0.41
     glo
    0.41
    POSITIVE LOGITS
    鹧
    0.63
     łat
    0.50
    عبير
    0.49
     résult
    0.47
    DELTA
    0.47
    碾
    0.46
    원에서
    0.45
    isierte
    0.45
    icità
    0.45
    全力
    0.45
    Activations Density 0.000%

    No Known Activations