© 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. 85204
    Prev
    Next
    INDEX
    Explanations

    buy or death

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

    local services or chicken skin

    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
    蝠
    0.51
     ойнотуу
    0.50
    Pharmaceutical
    0.49
     Energy
    0.49
    Energy
    0.49
    Sustainability
    0.48
     उम्मीदवार
    0.48
    Late
    0.48
     ಔಷಧ
    0.47
     ওষুধ
    0.47
    POSITIVE LOGITS
     hostel
    0.47
     convivial
    0.47
     \
    0.47
    gery
    0.46
     fraternal
    0.46
     cheerful
    0.46
     inquest
    0.46
    0.46
     encour
    0.46
     colt
    0.45
    Activations Density 0.001%

    No Known Activations