© 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. 142629
    Prev
    Next
    INDEX
    Explanations

    linking or listing items

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

    timeline, chaos, win, confidence

    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
    bedaan
    0.52
    мор
    0.47
    Ⲟ
    0.47
    interaction
    0.47
    uffix
    0.47
    ят
    0.46
    suffixes
    0.46
    ,#
    0.46
    itative
    0.45
    était
    0.45
    POSITIVE LOGITS
     Ghosts
    0.50
     Liu
    0.48
     Avalanche
    0.44
     gastronomic
    0.44
     volcano
    0.43
     enlarge
    0.42
    展開
    0.42
     Torrent
    0.42
    ِل
    0.42
     trợ
    0.41
    Activations Density 0.001%

    No Known Activations