© 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. 144105
    Prev
    Next
    INDEX
    Explanations

    during

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

    during and after certain words

    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
    도
    0.55
    Т
    0.50
    ಾಗಿದೆ
    0.49
    КА
    0.48
    needs
    0.48
    МО
    0.47
    새
    0.47
    Щ
    0.47
    Stabilise
    0.47
    К
    0.47
    POSITIVE LOGITS
     während
    0.53
     φ
    0.49
     during
    0.47
     durante
    0.46
     tijdens
    0.45
     phường
    0.44
     DURING
    0.44
     podczas
    0.44
     ตาม
    0.43
     tijekom
    0.43
    Activations Density 0.006%

    No Known Activations