© 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. 69604
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron fires specifically on occurrences of the identifier “status” (and its capitalized form) in code contexts.

    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
    </strong>
    -1.63
    utiva
    -1.62
     cuyas
    -1.58
    TBA
    -1.45
    ftrag
    -1.40
    StoryboardSegue
    -1.37
    ONLY
    -1.35
    俟
    -1.34
    ggio
    -1.34
     stadt
    -1.34
    POSITIVE LOGITS
    これらの
    1.77
     a
    1.76
     they
    1.70
    這些
    1.52
    他们
    1.41
     estas
    1.36
    on
    1.34
    WRENCE
    1.34
     on
    1.33
    無法
    1.33
    Activations Density 0.038%

    No Known Activations