© 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. 221151
    Prev
    Next
    INDEX
    Explanations

    story of people

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

    words preceding specific follow-ups

    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
     W
    0.64
     E
    0.57
     P
    0.53
     S
    0.52
     M
    0.51
     H
    0.51
     N
    0.50
     L
    0.49
     R
    0.47
     dur
    0.47
    POSITIVE LOGITS
    ສາມາດ
    0.58
    ﺰ
    0.54
    डू
    0.52
    expat
    0.52
    ⛵
    0.51
    🇿
    0.50
    ρω
    0.50
    mavros
    0.50
    核
    0.50
    🇰
    0.50
    Activations Density 0.001%

    No Known Activations