© 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. 225339
    Prev
    Next
    INDEX
    Explanations

    employees, survivors, jobs

    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
     BANKS
    0.48
     امتیاز
    0.47
     Fonction
    0.46
     احسن
    0.46
    킴
    0.45
     kitt
    0.45
    ースト
    0.45
     왼
    0.44
     Dopo
    0.44
     Conductivity
    0.44
    POSITIVE LOGITS
    fl
    0.56
    м
    0.49
    tiny
    0.49
    sil
    0.47
    ρο
    0.47
    dml
    0.47
     pensando
    0.46
    dv
    0.45
    sdale
    0.45
    aligned
    0.45
    Activations Density 0.000%

    No Known Activations