© 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. 102964
    Prev
    Next
    INDEX
    Explanations

    understated, crime, indicators, China

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

    latest software updates, according to numbers

    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
     bai
    0.49
    یع
    0.47
    니까
    0.47
    干扰
    0.45
     responseObject
    0.43
    Ｅ
    0.43
    谏
    0.43
    ཋ
    0.43
     Carlsbad
    0.43
     امنیت
    0.43
    POSITIVE LOGITS
    h
    0.55
    described
    0.52
    {
    0.51
    software
    0.49
    ch
    0.47
    defn
    0.47
     resulted
    0.47
    বল
    0.47
    k
    0.47
    mapped
    0.46
    Activations Density 0.000%

    No Known Activations