© 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. 22-GEMMASCOPE-RES-131K
    7. 28096
    Prev
    Next
    INDEX
    Explanations

    and his

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

    This neuron responds to numerical tokens (numbers) in the text.

    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
     it
    -1.17
    どちらも
    -1.14
     yanlış
    -1.09
     også
    -1.05
     Griechen
    -1.04
    Zubereitung
    -1.02
    両方
    -1.02
    Both
    -1.02
     они
    -1.01
     they
    -1.00
    POSITIVE LOGITS
     other
    2.39
     others
    2.05
     his
    1.90
     autres
    1.62
     lainnya
    1.60
     دیگر
    1.52
    otros
    1.50
     diğer
    1.49
     anderen
    1.47
     други
    1.44
    Activations Density 0.043%

    No Known Activations