© 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. 113973
    Prev
    Next
    INDEX
    Explanations

    engineer project

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

    lists, punctuation, and dates

    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
    ،
    0.45
     也
    0.45
     solidar
    0.44
     vaccinate
    0.43
     peasant
    0.43
    ECTORS
    0.42
     devote
    0.41
     också
    0.41
     activists
    0.41
     trabalhadores
    0.41
    POSITIVE LOGITS
    ソフトウェア
    0.50
    尝
    0.49
    개의
    0.46
     wyświet
    0.46
     स्वचालित
    0.46
    วัต
    0.45
     υψη
    0.44
    是在
    0.44
     வழங்கப்படும்
    0.44
    未经
    0.43
    Activations Density 0.002%

    No Known Activations