© 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. 221015
    Prev
    Next
    INDEX
    Explanations

    academic concepts and terms

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

    Atmospheric wave propagation

    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
     politič
    0.49
     tenían
    0.48
    yó
    0.48
    jecha
    0.48
    Detach
    0.48
    쏙
    0.47
     कामया
    0.47
    hadas
    0.47
    hna
    0.46
     सहमत
    0.46
    POSITIVE LOGITS
    ك
    0.45
    isch
    0.43
    ocole
    0.43
     PSA
    0.43
     σχ
    0.42
     una
    0.42
     transmitters
    0.41
     beck
    0.40
    italization
    0.40
     LIF
    0.40
    Activations Density 0.000%

    No Known Activations