© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83781
    Prev
    Next
    INDEX
    Explanations

    in the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    瑒
    -2.13
    菹
    -1.77
    懨
    -1.76
     that
    -1.65
    Ꮗ
    -1.61
    裢
    -1.57
    ownload
    -1.54
    Izuku
    -1.54
     podía
    -1.53
     vivía
    -1.53
    POSITIVE LOGITS
     of
    2.52
    the
    1.50
     he
    1.43
    -
    1.41
    手で
    1.36
    はこの
    1.34
     is
    1.32
     I
    1.32
     such
    1.32
    ra
    1.30
    Activations Density 0.415%

    No Known Activations