© 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. 123990
    Prev
    Next
    INDEX
    Explanations

    specific words followed by punctuation or conjunctions

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

    structured data and recursion

    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
    厚
    0.46
    差异
    0.40
    汐
    0.40
    ualmente
    0.40
    步骤
    0.40
     thận
    0.40
    ších
    0.40
    ície
    0.40
    挑戰
    0.40
    沉
    0.38
    POSITIVE LOGITS
     Zoo
    0.53
     Kremlin
    0.49
     Klan
    0.48
     Gmail
    0.47
     Rü
    0.47
     Afgan
    0.47
     Commiss
    0.46
    logfile
    0.46
     Distillery
    0.46
     orphanage
    0.46
    Activations Density 0.001%

    No Known Activations