© 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. 213203
    Prev
    Next
    INDEX
    Explanations

    Yalikavak, offering, bathrobe, lemonade

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

    distributional semantics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    0.53
     is
    0.46
     nga
    0.46
     as
    0.46
     due
    0.44
     và
    0.44
     ısı
    0.44
    얼
    0.44
     artigos
    0.43
    规
    0.43
    POSITIVE LOGITS
    ochromatic
    0.48
    borhood
    0.47
     ფედერ
    0.46
    cosec
    0.45
     খুঁজতে
    0.45
     स्वातंत्र
    0.45
    ូប
    0.45
     შემთხვევ
    0.45
    armonic
    0.44
     वृंदा
    0.44
    Activations Density 0.001%

    No Known Activations