© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70593
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron primarily detects long runs of whitespace (e.g. indentation or multi‐space formatting) in code or document text.

    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
    <td>
    -2.63
    ization
    -2.50
    RIES
    -2.38
     Lokasi
    -2.34
    Of
    -2.25
    ção
    -2.23
     Of
    -2.23
    <bos>
    -2.22
     On
    -2.17
     Mahasiswa
    -2.17
    POSITIVE LOGITS
    enablog
    2.70
    {
    2.64
    槼
    2.63
    峮
    2.56
     вышла
    2.52
    튿
    2.42
    ズニー
    2.33
    喑
    2.28
    褙
    2.28
     brancas
    2.25
    Activations Density 0.137%

    No Known Activations