© 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. 56625
    Prev
    Next
    INDEX
    Explanations

    professor titles and academic positions

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

    professor tenure awards

    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
     तहसीलदार
    0.45
    队员
    0.44
    ндары
    0.43
     Dustin
    0.42
    Serv
    0.41
    зульта
    0.40
    Donor
    0.40
    Volunteer
    0.40
    瓠
    0.40
    Benzoimidazol
    0.39
    POSITIVE LOGITS
     Professors
    0.62
    Professor
    0.59
     Professor
    0.57
    教授
    0.57
     professors
    0.55
     Profesor
    0.55
    院士
    0.53
     profesor
    0.52
     கோ
    0.51
     Unesco
    0.50
    Activations Density 0.079%

    No Known Activations