© 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. 87021
    Prev
    Next
    INDEX
    Explanations

    follows is

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

    sequences, code, or specific structures

    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
    ជាតិ
    0.53
    沍
    0.50
    證
    0.46
     complementar
    0.46
     छापेमारी
    0.46
     Validación
    0.44
    證據
    0.44
    лога
    0.44
     đốt
    0.44
    чит
    0.43
    POSITIVE LOGITS
    '
    0.55
     Beyonce
    0.55
     prese
    0.54
    ’
    0.51
    자
    0.50
    an
    0.50
     Sparta
    0.49
     Beyoncé
    0.48
     Montana
    0.48
     rework
    0.48
    Activations Density 0.000%

    No Known Activations