© 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. 250409
    Prev
    Next
    INDEX
    Explanations

    products and services

    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
    सर्गिक
    0.48
    ấu
    0.46
    őz
    0.45
     hứng
    0.45
     đón
    0.45
    épaisseur
    0.45
    सुम
    0.45
    ழுத
    0.44
    !/"
    0.44
    екси
    0.44
    POSITIVE LOGITS
     e
    0.58
     dos
    0.51
     film
    0.50
     email
    0.49
     movie
    0.49
    klu
    0.47
     ham
    0.47
     audiovisual
    0.47
     agreeable
    0.46
     equipment
    0.46
    Activations Density 0.001%

    No Known Activations