© 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. 71023
    Prev
    Next
    INDEX
    Explanations

    to verb or may verb

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

    fabrication, aunt, mobile mining, HR, project

    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
    un
    0.55
    unctional
    0.55
    la
    0.47
     a
    0.47
    uality
    0.45
    ość
    0.44
    zość
    0.44
    urut
    0.44
    die
    0.44
    :<
    0.43
    POSITIVE LOGITS
     ηλεκ
    0.55
     листо
    0.54
     這
    0.54
     patitth
    0.54
    已經
    0.52
     посмотре
    0.51
     त्यस
    0.51
    बंधनाच्या
    0.50
     የበለጠ
    0.50
     しっかり
    0.50
    Activations Density 0.000%

    No Known Activations