© 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. 119897
    Prev
    Next
    INDEX
    Explanations

    shall bind or loose

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

    business and regulatory terms

    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
     K
    0.52
     Slov
    0.50
     E
    0.48
    SOUTH
    0.47
     Phoen
    0.47
     Lorentz
    0.46
     Philadelphia
    0.46
     STEM
    0.45
    DO
    0.45
     Česk
    0.45
    POSITIVE LOGITS
    ற்போது
    0.48
     गव
    0.47
     алуу
    0.47
    spike
    0.47
    arote
    0.47
     {});
    0.46
     amenaza
    0.46
     ఇటీ
    0.46
     হুমকির
    0.45
    норийска
    0.45
    Activations Density 0.001%

    No Known Activations