© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11507
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by numeral or "containing"

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

    The neuron responds strongly to slash-delimited literals (e.g. regex patterns and file‐path strings).

    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
    _
    -1.32
    The
    -1.30
     begeistert
    -1.28
    /
    -1.27
    .,
    -1.27
    					
    -1.25
     работников
    -1.23
    賑
    -1.22
     wiederholt
    -1.20
    ~
    -1.20
    POSITIVE LOGITS
     also
    1.34
     siguran
    1.26
    OREM
    1.26
    ()");
    1.25
    Итак
    1.25
    mainwindow
    1.24
     inderdaad
    1.23
    herst
    1.21
    יע
    1.21
    termilk
    1.18
    Activations Density 0.050%

    No Known Activations