© 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. 205012
    Prev
    Next
    INDEX
    Explanations

    verb participial phrases

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

    directly connected

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ITHUB
    0.54
     मालिक
    0.52
     порядке
    0.51
    ENABLE
    0.50
    ఫ్
    0.50
    nh
    0.49
    >';
    0.48
     उसको
    0.48
     আরো
    0.47
    )';
    0.47
    POSITIVE LOGITS
     strain
    0.54
     gou
    0.53
     sip
    0.52
     race
    0.52
     species
    0.52
     gris
    0.50
     horrors
    0.50
     paw
    0.50
     cytology
    0.49
     aid
    0.48
    Activations Density 0.000%

    No Known Activations