© 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. 56688
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and continuations

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

    why things are used

    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
     H
    0.56
     öff
    0.54
    H
    0.52
    èse
    0.52
    âtre
    0.51
     母
    0.51
     apologize
    0.51
    hran
    0.51
     インド
    0.51
     ਅ
    0.50
    POSITIVE LOGITS
    ጿ
    0.57
    一提
    0.49
    jPanel
    0.49
     décadas
    0.48
     suspending
    0.46
    ાળા
    0.45
     belongings
    0.45
     spatially
    0.45
    عتها
    0.45
    iciente
    0.45
    Activations Density 0.000%

    No Known Activations