© 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. 250521
    Prev
    Next
    INDEX
    Explanations

    Runscope powered SDK

    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
    ík
    0.47
    icc
    0.45
    тки
    0.45
     電力
    0.45
     लाग
    0.44
     vaginale
    0.44
     Angaben
    0.44
    <0xBB>
    0.43
     Islamist
    0.43
    (()=>{
    0.43
    POSITIVE LOGITS
     recognizing
    0.47
     svom
    0.46
     this
    0.46
     reconhecimento
    0.45
     thefe
    0.43
    孳
    0.43
     čin
    0.43
    жон
    0.43
     recogn
    0.42
     questa
    0.42
    Activations Density 0.000%

    No Known Activations