© 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. 235372
    Prev
    Next
    INDEX
    Explanations

    following certain words

    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
    em
    0.59
    im
    0.56
    int
    0.54
    i
    0.51
    0
    0.50
    ux
    0.49
    Cox
    0.47
    granted
    0.46
    posit
    0.46
    orth
    0.46
    POSITIVE LOGITS
     ಕೊಡ
    0.51
     dorado
    0.51
     appease
    0.50
     हस्ता
    0.49
     అవకాశం
    0.49
     পদক্ষেপ
    0.49
    納税
    0.49
     これは
    0.48
    ૅ
    0.48
    輌
    0.48
    Activations Density 0.000%

    No Known Activations