© 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. 108192
    Prev
    Next
    INDEX
    Explanations

    to practice

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

    algebraic equations

    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
    诠
    0.52
    倘
    0.45
    舒适
    0.43
     raison
    0.42
    สบาย
    0.42
    是我
    0.42
    �
    0.40
    成长
    0.40
    дм
    0.40
    ́
    0.40
    POSITIVE LOGITS
     pradesh
    0.42
     ശക്തി
    0.42
     fasi
    0.42
    quard
    0.42
     nepř
    0.41
     نہيں
    0.41
     neuritis
    0.41
     radiolysis
    0.40
     ưu
    0.40
     Pubmed
    0.40
    Activations Density 0.000%

    No Known Activations