© 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-16K
    7. 11536
    Prev
    Next
    INDEX
    Explanations

    news and articles

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

    triple quotes for documentation

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dificultades
    0.54
     bataille
    0.50
     obtenue
    0.50
    otheli
    0.50
     facilidad
    0.50
     अंतराल
    0.50
     فتح
    0.49
     artériel
    0.49
     어
    0.48
    adihi
    0.48
    POSITIVE LOGITS
    5
    0.47
    "
    0.46
    SA
    0.43
    4
    0.43
    3
    0.43
    PR
    0.43
    BEL
    0.43
    :
    0.42
    *
    0.42
    ITS
    0.41
    Activations Density 0.007%

    No Known Activations