© 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. 113846
    Prev
    Next
    INDEX
    Explanations

    March surge

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

    sections: I. , II. , III

    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
     الحركة
    0.48
    模仿
    0.48
    說
    0.47
    pèce
    0.46
    প
    0.45
     حيث
    0.45
    一边
    0.45
    скольку
    0.45
     শহরে
    0.44
     মিঃ
    0.44
    POSITIVE LOGITS
     cor
    0.44
     kaisi
    0.44
     pok
    0.43
    ИА
    0.43
    ="/"
    0.42
     exploit
    0.42
     plaus
    0.41
    AssetsRequest
    0.41
     genetic
    0.41
    त्सा
    0.41
    Activations Density 0.001%

    No Known Activations