© 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. 235491
    Prev
    Next
    INDEX
    Explanations

    formal furniture

    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
     Zusätzlich
    0.47
     nicotine
    0.44
     vacanam
    0.43
     però
    0.43
     zusätzlich
    0.43
     preferred
    0.42
     disreg
    0.42
     indebtedness
    0.42
    但在
    0.41
    钬
    0.41
    POSITIVE LOGITS
    chart
    0.48
    फोर
    0.46
    autical
    0.46
    시켜
    0.46
    UTICAL
    0.45
    ╿
    0.45
    glomer
    0.45
    ╽
    0.45
    ANDS
    0.44
    끔
    0.44
    Activations Density 0.000%

    No Known Activations