© 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. 103093
    Prev
    Next
    INDEX
    Explanations

    introduce and assign

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

    The neuron selectively activates on numeric tokens (multi‐digit numbers or citation/reference counts) 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_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
     umožňuje
    -1.12
     kupa
    -1.11
     financieros
    -1.09
     páns
    -1.08
     kartą
    -1.08
     politika
    -1.05
     dámské
    -1.04
    greifen
    -1.04
     habló
    -1.04
     dáms
    -1.04
    POSITIVE LOGITS
     introduce
    2.00
     put
    1.98
     create
    1.83
    把
    1.83
    将
    1.80
     give
    1.78
     assign
    1.77
     use
    1.77
     gave
    1.76
     apply
    1.75
    Activations Density 0.193%

    No Known Activations