© 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. 221215
    Prev
    Next
    INDEX
    Explanations

    live music

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

    introductions and lists using colons

    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
    5
    0.54
    ता
    0.54
    Quint
    0.48
    黄金
    0.48
    esters
    0.47
    Could
    0.46
    6
    0.45
    icketts
    0.45
     personn
    0.44
    ection
    0.44
    POSITIVE LOGITS
    '])){
    0.51
    পূর্ন
    0.49
    '=>'
    0.49
     responder
    0.48
    dır
    0.47
     غير
    0.46
     trooper
    0.46
     EN
    0.46
     ':'
    0.45
    த்தில்
    0.45
    Activations Density 0.001%

    No Known Activations