© 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. 178401
    Prev
    Next
    INDEX
    Explanations

    news and current affairs

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

    vocabulary and warrants

    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
     रिवाइज
    0.45
     Astrology
    0.44
    UTONIUM
    0.43
     audiov
    0.43
     назначен
    0.43
     Assessing
    0.42
     shogun
    0.42
     आजकल
    0.42
     potrav
    0.42
    抨
    0.42
    POSITIVE LOGITS
    anı
    0.59
    ç
    0.55
    "
    0.50
    ag
    0.49
    çam
    0.49
    л
    0.48
    щ
    0.48
    ﺩ
    0.48
    anız
    0.47
    ısına
    0.46
    Activations Density 0.000%

    No Known Activations