© 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. 150043
    Prev
    Next
    INDEX
    Explanations

    actions like click, log, add

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

    complex mechanisms and structures

    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
    躏
    0.49
     abusers
    0.48
     PKC
    0.44
     quantile
    0.43
     sepsis
    0.43
     movilidad
    0.43
     injury
    0.43
    㭐
    0.43
     mortality
    0.42
     yaptı
    0.42
    POSITIVE LOGITS
    tl
    0.52
    tied
    0.52
    tried
    0.52
    twice
    0.50
     थंड
    0.50
    ties
    0.49
    to
    0.49
    c
    0.48
    tag
    0.48
    tä
    0.48
    Activations Density 0.001%

    No Known Activations