© 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. 192610
    Prev
    Next
    INDEX
    Explanations

    curses and negative sentiment

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

    positive evaluation 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
    सार
    0.46
    ega
    0.46
    ESSAGE
    0.46
    address
    0.45
    哃
    0.45
     जलाश
    0.44
    Address
    0.44
     مرتب
    0.44
    Conversion
    0.44
    erves
    0.44
    POSITIVE LOGITS
    ர்ஸ்
    0.51
     insecurities
    0.50
    šení
    0.49
    ड़ों
    0.46
     swipes
    0.45
     bleue
    0.45
     ramping
    0.45
     séptimo
    0.45
    剣
    0.45
    ській
    0.44
    Activations Density 0.000%

    No Known Activations