© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86422
    Prev
    Next
    INDEX
    Explanations

    fifth graders and enterprise

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

    This neuron fires on markup for table cells or headers (e.g. `<th>`, `<td>`, and table-cell lines with pipes, colspan, align, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -1.55
     February
    -1.32
     what
    -1.29
    不得不
    -1.29
     ALL
    -1.26
     Mitteln
    -1.24
     its
    -1.20
     namorado
    -1.18
     without
    -1.16
     asesino
    -1.16
    POSITIVE LOGITS
     is
    1.75
    titial
    1.63
    …»
    1.56
    蛲
    1.52
     magnific
    1.52
    venant
    1.52
     память
    1.44
     AsyncTask
    1.41
    ఽ
    1.41
    たち
    1.39
    Activations Density 0.000%

    No Known Activations