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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    code and programming snippets

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

    The neuron is detecting runs of whitespace used for indentation (i.e. leading spaces/tabs in code).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     before
    -2.03
     those
    -1.85
     that
    -1.85
     with
    -1.83
     as
    -1.77
     by
    -1.70
     has
    -1.67
     at
    -1.63
     after
    -1.62
     like
    -1.61
    POSITIVE LOGITS
    為に
    1.56
    を選び
    1.52
     italiens
    1.52
     VERY
    1.44
     chô
    1.41
     hunne
    1.40
     magasiner
    1.39
    uré
    1.38
     !!!!
    1.37
     inconvénients
    1.37
    Activations Density 0.033%

    No Known Activations