© 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. 176946
    Prev
    Next
    INDEX
    Explanations

    problem then another

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

    industrial settings or verse

    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
    ᓲ
    0.51
    شل
    0.50
    ｪ
    0.50
    奐
    0.50
    瓔
    0.49
    يز
    0.49
    жко
    0.49
    ەر
    0.48
    崙
    0.48
    ᕋ
    0.47
    POSITIVE LOGITS
    ta
    0.54
    am
    0.53
     ...
    0.50
    tu
    0.49
     he
    0.48
    ti
    0.48
    :
    0.48
    do
    0.47
     an
    0.47
     同
    0.47
    Activations Density 0.001%

    No Known Activations