© 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. 119806
    Prev
    Next
    INDEX
    Explanations

    securely use smartphones

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

    security, completion, competition, fixation

    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
    Negative Logits
    蛋白质
    0.46
    ﻕ
    0.46
    ጠና
    0.43
    مل
    0.43
    Ava
    0.42
    үндө
    0.41
    ماس
    0.40
    ጣ
    0.40
    كون
    0.40
    ოვ
    0.39
    POSITIVE LOGITS
     शिफ्ट
    0.54
     ocorreu
    0.52
     desech
    0.46
     दायर
    0.46
     lệch
    0.46
     किमान
    0.45
     необхідно
    0.45
     অভিযুক্ত
    0.45
     அவசியம்
    0.44
     ስርዓ
    0.44
    Activations Density 0.001%

    No Known Activations