© 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. 198621
    Prev
    Next
    INDEX
    Explanations

    compound phrases and collocations

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

    dominant now

    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
    FIRE
    0.54
    ethical
    0.50
    доступ
    0.49
    法令
    0.49
    
    0.49
    useful
    0.48
    categ
    0.48
     رہنے
    0.47
    nutrient
    0.46
    権利
    0.46
    POSITIVE LOGITS
     Surgical
    0.44
     now
    0.44
     already
    0.43
     {
    0.43
     już
    0.42
     Soccer
    0.41
     Require
    0.40
     Softball
    0.40
     Blue
    0.40
     Shell
    0.40
    Activations Density 0.000%

    No Known Activations