© 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. 103707
    Prev
    Next
    INDEX
    Explanations

    She mastered, realized

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

    opposition, inflammation, closer, exposure, interactions

    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
    All
    0.47
     khoảng
    0.47
    会将
    0.47
    众
    0.46
    在
    0.46
     options
    0.46
    的
    0.46
    三个
    0.46
    线程
    0.45
    的情况下
    0.45
    POSITIVE LOGITS
    чис
    0.44
    rán
    0.44
    kovskij
    0.43
    calculated
    0.43
    opos
    0.43
     આન
    0.43
    istem
    0.43
    pell
    0.43
    rashed
    0.42
    regener
    0.42
    Activations Density 0.002%

    No Known Activations