© 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. 226526
    Prev
    Next
    INDEX
    Explanations

    delivery or save

    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
    é
    0.55
    ية
    0.54
     تغيير
    0.52
    formes
    0.52
    il
    0.51
    épaisseur
    0.51
    nés
    0.51
    í
    0.51
    mesi
    0.50
    rewsbury
    0.50
    POSITIVE LOGITS
     JFK
    0.46
     campaign
    0.45
     climbs
    0.45
     terminator
    0.44
     Bradshaw
    0.44
     starboard
    0.43
     WERE
    0.42
    在其
    0.42
     board
    0.42
     Brookhaven
    0.42
    Activations Density 0.000%

    No Known Activations