© 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. 29888
    Prev
    Next
    INDEX
    Explanations

    campus or student life

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

    education and childcare

    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
    Not in Any Lists

    No Comments

    Negative Logits
    或
    0.53
    טל
    0.52
     או
    0.48
     أو
    0.46
    이나
    0.46
    大多
    0.46
    하거나
    0.44
    AKE
    0.44
    Kung
    0.43
    俱
    0.43
    POSITIVE LOGITS
     ребенок
    0.51
    विद्यालय
    0.50
     помещения
    0.50
     eliminates
    0.49
     criança
    0.48
     student
    0.46
     dziecka
    0.45
     Campus
    0.45
     ক্যাম্পাস
    0.45
     campus
    0.45
    Activations Density 0.000%

    No Known Activations