© 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. 34-GEMMASCOPE-RES-131K
    7. 84951
    Prev
    Next
    INDEX
    Explanations

    calculating differences and remainders

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

    The neuron consistently activates on number tokens (digits and numeric values), signaling that it’s detecting numeric content.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    forKey
    -0.92
    adple
    -0.86
     tä
    -0.82
    familien
    -0.81
    жий
    -0.79
    ),),
    -0.78
    гур
    -0.78
     allem
    -0.78
     faut
    -0.78
     :</
    -0.77
    POSITIVE LOGITS
     difference
    0.99
    difference
    0.92
     decrease
    0.88
     rozdí
    0.85
    Subtract
    0.84
     разница
    0.79
    mathbf
    0.79
     subtract
    0.77
    Difference
    0.76
     Subtract
    0.75
    Activations Density 0.024%

    No Known Activations