© 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. 82896
    Prev
    Next
    INDEX
    Explanations

    beginnings of complex phrases

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

    explaining concepts

    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
    рисо
    0.50
     protagonistas
    0.49
    /
    0.47
     sonda
    0.44
    ricate
    0.44
    vedi
    0.43
    ಹಾ
    0.43
     잡아
    0.43
    댑
    0.43
     insanely
    0.43
    POSITIVE LOGITS
     quantities
    0.42
    阆
    0.41
     zwią
    0.40
     जिला
    0.40
    二年
    0.40
    ্যাম্প
    0.40
    服务
    0.40
     évaluation
    0.40
    earth
    0.39
    équipement
    0.39
    Activations Density 0.001%

    No Known Activations