© 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. 34-GEMMASCOPE-RES-131K
    7. 108537
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    This neuron detects long runs of space characters (i.e. indentation or large blocks of whitespace).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     in
    -1.52
     by
    -1.49
     from
    -1.48
     especially
    -1.46
     Each
    -1.42
     During
    -1.40
     However
    -1.38
     not
    -1.37
     When
    -1.33
     Those
    -1.32
    POSITIVE LOGITS
    {
    1.64
    {
    1.24
     weihnachten
    1.23
     vijf
    1.20
     スクエア
    1.18
    踯
    1.14
    糁
    1.14
     insanely
    1.13
    ků
    1.13
     {
    1.13
    Activations Density 0.008%

    No Known Activations