© 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. 205185
    Prev
    Next
    INDEX
    Explanations

    welcome

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

    definitions and instructions

    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
     appending
    0.51
    侙
    0.51
    kis
    0.50
    rition
    0.45
    ্থিত
    0.45
     శక్తి
    0.45
     Virology
    0.45
    訨
    0.45
     Irradiation
    0.44
    iedenis
    0.44
    POSITIVE LOGITS
    일까지
    0.58
     PTC
    0.51
    점
    0.50
    점을
    0.50
    க்கு
    0.49
    까지
    0.48
    교
    0.47
    日程
    0.46
     marquee
    0.46
    하루
    0.45
    Activations Density 0.000%

    No Known Activations