© 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. 63458
    Prev
    Next
    INDEX
    Explanations

    number of occurrences

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

    explosions and fires

    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
    esters
    0.45
    es
    0.40
    gens
    0.39
    istant
    0.38
     danse
    0.38
    verture
    0.38
     daerah
    0.38
     ampere
    0.38
    {
    0.38
     ovaries
    0.37
    POSITIVE LOGITS
    两次
    0.52
    三次
    0.49
     במהלך
    0.49
    ócio
    0.47
     हमने
    0.46
     વખત
    0.46
     során
    0.46
     उसने
    0.45
     时
    0.44
     ഒരിക്ക
    0.43
    Activations Density 0.000%

    No Known Activations