© 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. 63165
    Prev
    Next
    INDEX
    Explanations

    categories and specific items

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

    global centers

    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
     tob
    0.47
     freeing
    0.47
     be
    0.45
     hand
    0.45
     tox
    0.45
     compi
    0.45
     o
    0.44
     it
    0.44
     unplug
    0.44
     one
    0.43
    POSITIVE LOGITS
    RIBUTION
    0.52
    मोहन
    0.50
    पोस्ट
    0.48
     নির্বাচ
    0.47
    امة
    0.47
    ुत
    0.47
    anzitutto
    0.46
     سلاټ
    0.46
    ام
    0.46
    نوع
    0.45
    Activations Density 0.001%

    No Known Activations