© 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. 180160
    Prev
    Next
    INDEX
    Explanations

    common functional words

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

    preserving, not, expanding

    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
     constate
    0.50
    បំ
    0.48
     považ
    0.48
    𐰣
    0.48
     បាន
    0.47
    Contrast
    0.46
     tren
    0.46
    Brains
    0.46
    sframe
    0.46
     ਤ
    0.46
    POSITIVE LOGITS
    elj
    0.49
    ровая
    0.45
    oj
    0.45
    вная
    0.45
    жная
    0.45
    ියා
    0.45
    남도
    0.44
    aters
    0.44
    ו
    0.44
    ιά
    0.43
    Activations Density 0.001%

    No Known Activations