© 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. 87210
    Prev
    Next
    INDEX
    Explanations

    serial number

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

    specifically programmed

    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
    ið
    0.54
     κα
    0.51
    től
    0.50
     เนื่องจาก
    0.50
     colocando
    0.49
     Tochter
    0.49
     essentielle
    0.49
     Ме
    0.48
    𝒕
    0.48
     inasmuch
    0.48
    POSITIVE LOGITS
     visibly
    0.46
    벤트
    0.43
    曳
    0.43
    fileExistsAtPath
    0.42
    -(
    0.41
    .([]
    0.41
    뇰
    0.41
    出来
    0.41
    щены
    0.41
    飼
    0.41
    Activations Density 0.000%

    No Known Activations