© 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. 150059
    Prev
    Next
    INDEX
    Explanations

    form of, alcohol testing, NFC labels

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

    creates new images

    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
     nm
    0.48
    μ
    0.48
     ultimatum
    0.48
    nm
    0.46
     embryo
    0.46
     altercation
    0.46
     acrobat
    0.45
     ivory
    0.44
     মনোর
    0.43
    nın
    0.43
    POSITIVE LOGITS
    ду
    0.47
    檤
    0.47
    蔭
    0.45
     دي
    0.44
    TEC
    0.44
     запол
    0.44
    നാള
    0.43
    gever
    0.43
     जीवनी
    0.42
    စျေး
    0.42
    Activations Density 0.001%

    No Known Activations