© 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. 212103
    Prev
    Next
    INDEX
    Explanations

    time, legal, city, appeal

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

    let it

    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
    4
    0.50
     Bangladeshi
    0.48
     Libyan
    0.46
     Egyptian
    0.45
    henge
    0.45
     bile
    0.44
     Disposal
    0.44
     nowrap
    0.43
     bleach
    0.42
    bile
    0.42
    POSITIVE LOGITS
    মাস
    0.54
    स्टेप
    0.52
    ترك
    0.51
    ন
    0.51
    ன
    0.51
    ვ
    0.50
    総合
    0.50
     ፓ
    0.49
    στα
    0.48
    ുട
    0.48
    Activations Density 0.000%

    No Known Activations