© 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. 221005
    Prev
    Next
    INDEX
    Explanations

    description of things or entities

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

    acknowledgement feels good

    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
     покрытия
    0.57
    プ
    0.51
     победи
    0.48
     المُ
    0.46
     convexe
    0.46
    λευτα
    0.46
     શહે
    0.46
    empot
    0.45
    婦
    0.45
    瘡
    0.45
    POSITIVE LOGITS
     infall
    0.49
     Electricity
    0.47
     jinak
    0.47
     Ontario
    0.46
     Ripp
    0.46
     oss
    0.45
    র্ত
    0.44
     babel
    0.44
    inference
    0.44
     Babel
    0.44
    Activations Density 0.001%

    No Known Activations