© 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. 82705
    Prev
    Next
    INDEX
    Explanations

    flying squirrels

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

    information gathering and communication

    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
    ಾದರೆ
    0.51
     Hotspur
    0.49
     électronique
    0.46
     Ici
    0.46
     froide
    0.46
     人気
    0.45
     zaken
    0.45
     付
    0.45
     で
    0.44
     lui
    0.44
    POSITIVE LOGITS
    飧
    0.49
     VILL
    0.47
     ramb
    0.46
    sett
    0.43
     TAP
    0.43
     fidd
    0.43
    所有的
    0.43
     আল্লাহ
    0.43
     REND
    0.43
     रामबा
    0.43
    Activations Density 0.002%

    No Known Activations