© 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. 187354
    Prev
    Next
    INDEX
    Explanations

    geometri, Kafka, fotografi

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

    absolute peace

    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
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.61
    ন
    0.56
    ला
    0.54
    ด
    0.54
    ن
    0.52
    م
    0.50
    د
    0.50
    ು
    0.50
    ل
    0.48
    ر
    0.48
    POSITIVE LOGITS
     факт
    0.48
     geometri
    0.46
     }{}_{\
    0.44
    दर्शिता
    0.43
     Kafka
    0.43
     સમજ
    0.43
     समानार्थी
    0.43
     बेटियों
    0.42
     રાખી
    0.42
    üm
    0.42
    Activations Density 0.000%

    No Known Activations