© 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. 193206
    Prev
    Next
    INDEX
    Explanations

    just followed by a word

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

    just simply or justification

    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
    ти
    0.46
     линию
    0.46
     スリム
    0.45
    лни
    0.43
    盞
    0.43
    稚
    0.43
    дом
    0.42
    ਥ
    0.42
     サイド
    0.41
    kses
    0.41
    POSITIVE LOGITS
    Stats
    0.47
    ایر
    0.45
    لاست
    0.45
    speakers
    0.44
    Speakers
    0.44
     hätten
    0.44
    {~
    0.44
     వెళ్లి
    0.43
    Games
    0.43
    श्रेष्ठ
    0.42
    Activations Density 0.002%

    No Known Activations