© 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. 166641
    Prev
    Next
    INDEX
    Explanations

    state or country

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

    Azur Lane, cold glass, pasta, dynamic fields

    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
     व्यावसायिक
    0.50
     سنگ
    0.49
    쓰
    0.47
     Cran
    0.44
     보통
    0.43
    다음
    0.43
     patric
    0.43
     ප්‍රති
    0.43
     സാധാരണ
    0.43
     普通
    0.43
    POSITIVE LOGITS
    ígen
    0.50
    Minus
    0.43
    ⃣
    0.42
    睐
    0.41
    であることを
    0.41
    ornis
    0.41
     चुके
    0.40
    વિધ
    0.40
    FBSDKLogin
    0.40
     яке
    0.40
    Activations Density 0.000%

    No Known Activations