© 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. 176495
    Prev
    Next
    INDEX
    Explanations

    Farm Tour

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

    put in

    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
    ว่า
    0.52
    राम
    0.52
    Deletion
    0.52
    PhotoMode
    0.51
    सोबत
    0.51
    Cherry
    0.51
    ↕
    0.48
    ר
    0.48
    ী
    0.47
    Quad
    0.47
    POSITIVE LOGITS
    ening
    0.49
     близ
    0.46
     fuer
    0.44
     dwellings
    0.43
     eind
    0.42
    cemic
    0.42
     Institutional
    0.42
     intoxicating
    0.41
    eties
    0.41
    mates
    0.41
    Activations Density 0.002%

    No Known Activations