© 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. 22-GEMMASCOPE-RES-131K
    7. 38877
    Prev
    Next
    INDEX
    Explanations

    `CASE`, `id`, `latitude`, `Add`

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

    This neuron fires on numeric tokens (i.e. literal numbers) in code or markup.

    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
     possibly
    -0.84
    ktive
    -0.83
     wanting
    -0.80
    жко
    -0.79
     maybe
    -0.78
     necesarias
    -0.77
     दिए
    -0.75
     there
    -0.73
     that
    -0.73
     sencillas
    -0.73
    POSITIVE LOGITS
    ForType
    0.91
    媽
    0.89
    ߋ
    0.87
    Yao
    0.84
     meow
    0.82
    vän
    0.82
     WRONG
    0.80
    顱
    0.80
     reas
    0.80
     AGAIN
    0.79
    Activations Density 0.013%

    No Known Activations