© 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. 22-GEMMASCOPE-RES-131K
    7. 129304
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (digits/number tokens) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     terenie
    -0.94
    &&&
    -0.83
    ☑
    -0.83
     otherwise
    -0.81
     לעשות
    -0.81
     number
    -0.80
    "}")
    -0.78
     образова
    -0.78
     "("
    -0.78
    سات
    -0.77
    POSITIVE LOGITS
     presso
    0.91
    ujuk
    0.91
     понадоби
    0.88
    نکته
    0.87
    פשר
    0.87
    Zutaten
    0.86
     ditetapkan
    0.86
     untranslated
    0.85
    Причины
    0.85
    rikt
    0.84
    Activations Density 0.006%

    No Known Activations