© 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. 208041
    Prev
    Next
    INDEX
    Explanations

    of diabetes medicine

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

    sperm meets egg

    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
     $
    0.50
     निमित
    0.49
    atomic
    0.44
    appl
    0.44
    iya
    0.43
     RG
    0.43
    broadcast
    0.43
    apeutic
    0.42
    durch
    0.42
    acent
    0.42
    POSITIVE LOGITS
    ोज़
    0.50
    想起
    0.47
    കൻ
    0.46
    잤
    0.46
    േഷൻ
    0.45
     něj
    0.45
    ohan
    0.45
     érté
    0.45
     значення
    0.44
     nahilalakip
    0.44
    Activations Density 0.001%

    No Known Activations