© 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. 212179
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ, average height

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

    NFT buyer

    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
     Œ
    0.43
    到时候
    0.42
    분이
    0.42
    乐队
    0.41
     Chocol
    0.41
     Healey
    0.40
     Bazaar
    0.40
     Childs
    0.40
    元
    0.39
    度が
    0.39
    POSITIVE LOGITS
     ด่า
    0.52
     morreu
    0.50
     sniffing
    0.50
    overwrite
    0.48
     প্রয়
    0.48
     שני
    0.47
    covariant
    0.47
     ちゃう
    0.46
    traces
    0.46
    нал
    0.46
    Activations Density 0.001%

    No Known Activations