© 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. 215979
    Prev
    Next
    INDEX
    Explanations

    disputed domain names

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

    code cells, survivors, offerings

    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
    В
    0.55
    ვე
    0.47
     novella
    0.46
    GENERAL
    0.46
    맏
    0.45
    ㄼ
    0.44
     ancien
    0.44
     Règles
    0.43
    他の
    0.43
    ınar
    0.43
    POSITIVE LOGITS
     這
    0.51
     combustion
    0.47
    োগ্র
    0.47
     بود
    0.47
     slats
    0.46
     بودند
    0.46
     measurement
    0.45
    tenths
    0.45
     هست
    0.45
     भि
    0.44
    Activations Density 0.000%

    No Known Activations