© 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. 184929
    Prev
    Next
    INDEX
    Explanations

    measures related to time and finance

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

    breaking down into sentences

    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
     کردند
    0.48
     vasculature
    0.45
     a
    0.45
     podium
    0.44
    zza
    0.43
    resources
    0.43
     تھے
    0.43
    increment
    0.42
     clear
    0.42
    iori
    0.42
    POSITIVE LOGITS
    企业的
    0.55
    മാന
    0.43
     მ
    0.42
     మరియు
    0.42
    笑着
    0.42
     codzien
    0.42
     satış
    0.42
    گیری
    0.41
     aggrav
    0.40
    ጠቃ
    0.40
    Activations Density 0.001%

    No Known Activations