© 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. 83720
    Prev
    Next
    INDEX
    Explanations

    Q, Veg, Pre, Hyper, 2

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

    The neuron flags wiki markup template delimiters (the double‐brace “{{…}}” template/infobox syntax).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    </h3>
    -1.68
     perpé
    -1.61
     oike
    -1.53
    ':
    -1.50
    )."
    -1.46
    rabh
    -1.45
     "]
    -1.44
    aran
    -1.41
     exercer
    -1.39
     IBRARY
    -1.39
    POSITIVE LOGITS
     “
    1.52
     もう
    1.44
    ↵
    1.38
     ‘’
    1.35
     that
    1.32
     ”
    1.31
     cavallo
    1.30
    は
    1.30
    それは
    1.29
    with
    1.27
    Activations Density 0.000%

    No Known Activations