© 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. 191080
    Prev
    Next
    INDEX
    Explanations

    prior to

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

    vulnerabilities, community, raiding villages, condition, camera app, notes, garage, nginx

    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
     adicionar
    0.57
    т
    0.51
     aiz
    0.49
    ಾಯಿತು
    0.49
    鋃
    0.49
    дон
    0.49
    нт
    0.48
    ताई
    0.47
    ញ្
    0.46
    abut
    0.46
    POSITIVE LOGITS
     Garage
    0.49
     garage
    0.43
    wege
    0.42
     শুন
    0.41
     Hobbes
    0.41
    Garage
    0.40
    onie
    0.40
     योग्य
    0.39
     Ligue
    0.39
    --
    0.39
    Activations Density 0.002%

    No Known Activations