© 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. 81725
    Prev
    Next
    INDEX
    Explanations

    operational contexts

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

    increasingly, greatly, quietly, quickly

    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
    '
    0.51
    仮
    0.45
    ｫ
    0.45
    kina
    0.41
    {
    0.40
    organisms
    0.40
    員
    0.39
    覚
    0.39
    posterior
    0.39
    TestingModule
    0.38
    POSITIVE LOGITS
     increasingly
    0.52
     dificult
    0.52
     quieter
    0.51
     greatly
    0.50
     वृद्धि
    0.49
     बढ़ती
    0.49
     वाढत
    0.49
     endearing
    0.49
     quietly
    0.48
     трудно
    0.48
    Activations Density 0.002%

    No Known Activations