© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128987
    Prev
    Next
    INDEX
    Explanations

    kills viruses and bacteria

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

    lost soul, enigmatic master

    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
     чыныгы
    0.55
    āng
    0.50
     fonbet
    0.50
     законода
    0.49
     سلاټ
    0.47
    istocene
    0.47
    $.;
    0.46
     شرطونه
    0.45
    .").
    0.45
    erdere
    0.44
    POSITIVE LOGITS
    g
    0.61
    r
    0.57
    b
    0.54
    d
    0.53
    ط
    0.53
    j
    0.50
    k
    0.50
    i
    0.49
    ll
    0.45
    l
    0.45
    Activations Density 0.000%

    No Known Activations