© 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. 178467
    Prev
    Next
    INDEX
    Explanations

    who were

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

    reporting factual information

    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
     Tento
    0.55
    discard
    0.52
    および
    0.48
     usuário
    0.48
    Ciao
    0.48
     utenti
    0.47
    NOTA
    0.47
     Benutzer
    0.46
     consente
    0.46
    Н
    0.46
    POSITIVE LOGITS
     arbitr
    0.40
     সেনাবাহিনী
    0.39
     vital
    0.39
     Wealth
    0.38
     accountability
    0.37
     responsiveness
    0.37
     atom
    0.37
    ោង
    0.37
     wealth
    0.37
     Zeitung
    0.36
    Activations Density 0.001%

    No Known Activations