© 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. 166728
    Prev
    Next
    INDEX
    Explanations

    contextual phrases

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

    calculate moles of

    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
    丰
    0.53
    乡
    0.48
    疯
    0.48
    直线
    0.47
    拢
    0.47
    赐
    0.46
    易
    0.46
    风
    0.45
    商
    0.44
    疏
    0.44
    POSITIVE LOGITS
    basi
    0.51
    situ
    0.50
    maat
    0.48
     lids
    0.47
     سری
    0.46
    situation
    0.45
     অবস্থা
    0.44
    beforeend
    0.44
     اسرائیلی
    0.44
    material
    0.44
    Activations Density 0.001%

    No Known Activations