© 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. 90844
    Prev
    Next
    INDEX
    Explanations

    times followed by a colon

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

    dates and times

    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
    Для
    0.52
    Й
    0.52
    โพ
    0.51
    Kennedy
    0.51
    Ш
    0.51
    KURZ
    0.50
    З
    0.49
    Э
    0.48
    Kurt
    0.47
    netHex
    0.47
    POSITIVE LOGITS
     Rates
    0.51
    aceae
    0.50
     Nights
    0.50
     Breakfast
    0.43
     Types
    0.43
     nights
    0.42
     Thesis
    0.42
     Sleeping
    0.42
    လိ
    0.41
     दरों
    0.41
    Activations Density 0.001%

    No Known Activations