© 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. 102980
    Prev
    Next
    INDEX
    Explanations

    with or by

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

    if understood that

    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
     superblock
    0.45
    Wg
    0.45
     सबकुछ
    0.45
    ক্তি
    0.44
    రుగులు
    0.44
    ेंद्रीय
    0.44
     redwood
    0.44
    arakatuh
    0.43
    ]]),
    0.43
     onRequest
    0.43
    POSITIVE LOGITS
    ado
    0.52
    uras
    0.47
     ก
    0.47
    armed
    0.44
    bonded
    0.43
    ones
    0.43
     bonded
    0.43
    angel
    0.42
    fic
    0.42
     sogen
    0.42
    Activations Density 0.000%

    No Known Activations