© 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. 139801
    Prev
    Next
    INDEX
    Explanations

    true testament

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

    addressing you directly

    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
    excel
    0.47
    ate
    0.46
     endoscopic
    0.45
    od
    0.45
    llä
    0.44
    indon
    0.44
    atte
    0.43
    extreme
    0.43
     abortion
    0.42
    (
    0.42
    POSITIVE LOGITS
     Мар
    0.54
     собственные
    0.54
     линии
    0.52
     Хар
    0.52
    ние
    0.51
     ahuv
    0.51
     издание
    0.51
     પ્રે
    0.50
    雇
    0.50
     рэ
    0.50
    Activations Density 0.001%

    No Known Activations