© 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. 185190
    Prev
    Next
    INDEX
    Explanations

    regularly say, compared with

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

    market volatility

    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
    Cuando
    0.54
     slowed
    0.51
    Ketika
    0.51
     parlano
    0.49
    屒
    0.48
     Cuando
    0.48
     وقل
    0.46
     देगी
    0.46
    娣
    0.45
     Ahora
    0.45
    POSITIVE LOGITS
    ीय
    0.56
    ी
    0.51
    ์
    0.49
    ändig
    0.48
    gewicht
    0.48
    fahrt
    0.47
    handlung
    0.47
    zigzag
    0.46
    ूले
    0.46
    ią
    0.46
    Activations Density 0.000%

    No Known Activations