© 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. 185584
    Prev
    Next
    INDEX
    Explanations

    geographic coordinates

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

    contrasting conjunctions

    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
    el
    0.56
    Can
    0.56
    I
    0.55
    cl
    0.54
     can
    0.54
     %>%
    0.54
    Regist
    0.54
    Row
    0.53
    Ὅ
    0.53
    Editor
    0.52
    POSITIVE LOGITS
    走行
    0.50
    缺
    0.48
    ない
    0.47
     desorption
    0.46
     televised
    0.46
     lintas
    0.46
    atthena
    0.45
     actuation
    0.45
    রাও
    0.45
     เส้น
    0.44
    Activations Density 0.001%

    No Known Activations