© 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. 87032
    Prev
    Next
    INDEX
    Explanations

    adds flavor or describes material

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

    globbing, causing, cetaceans, skunks, glass

    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
    uet
    0.50
     fluctuation
    0.48
    uvat
    0.44
     แรง
    0.42
    ο
    0.42
    ेड
    0.42
    শত
    0.41
    Seite
    0.41
    intelligent
    0.40
    >≥</
    0.40
    POSITIVE LOGITS
     bá
    0.49
     composição
    0.48
     exd
    0.45
     electroly
    0.45
     josé
    0.44
     şöyle
    0.44
    adería
    0.43
     éx
    0.43
     złoż
    0.43
     breakfasts
    0.42
    Activations Density 0.000%

    No Known Activations