© 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. 71134
    Prev
    Next
    INDEX
    Explanations

    July admitted

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

    undergarments and foreign organisms

    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
    жают
    0.50
    женные
    0.44
     militias
    0.44
    щают
    0.43
    یکم
    0.42
    りは
    0.42
    نن
    0.41
    𝙣
    0.41
     نن
    0.41
     vegetarians
    0.41
    POSITIVE LOGITS
     Helsing
    0.49
    ด้
    0.47
     Television
    0.46
    blacklist
    0.45
    াচিত
    0.45
    ingham
    0.43
     Morty
    0.42
    厛
    0.42
     Stan
    0.42
    ȏ
    0.42
    Activations Density 0.000%

    No Known Activations