© 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. 103093
    Prev
    Next
    INDEX
    Explanations

    best, hunter, waste, enormous, positively, nerves, these, last, much

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

    list item markers

    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
     subalgebras
    0.48
    止め
    0.47
    已
    0.47
    に
    0.46
    检
    0.44
     overruled
    0.44
     equipments
    0.44
     organizações
    0.43
    ग्नो
    0.43
     permanente
    0.43
    POSITIVE LOGITS
    사와
    0.49
    isteria
    0.45
    뒷
    0.45
     பங்கு
    0.44
    và
    0.44
    auks
    0.43
    스와
    0.43
    %,
    0.43
    zesz
    0.42
     cable
    0.42
    Activations Density 0.000%

    No Known Activations