© 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. 146811
    Prev
    Next
    INDEX
    Explanations

    "last year" or "urgent teachers"

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

    Genesis, Translation, must, understand

    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
    ৬৫
    0.50
    主管部门
    0.46
    ки
    0.46
     добре
    0.44
     бизнеса
    0.44
     sails
    0.43
    Imports
    0.43
    𝙙
    0.42
    ministrazione
    0.42
    位
    0.42
    POSITIVE LOGITS
     positif
    0.48
    ρι
    0.45
     नोटबुक
    0.44
     medica
    0.44
    Budd
    0.43
     Persön
    0.42
     bud
    0.42
     Fahrrad
    0.42
     novella
    0.42
     doubt
    0.42
    Activations Density 0.000%

    No Known Activations