© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28596
    Prev
    Next
    INDEX
    Explanations

    lastly, finally, or at the end

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

    This neuron activates strongly on numerical tokens (integer values) wherever they appear 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
    っていましたが
    -1.18
     immediatamente
    -1.09
     объясня
    -1.09
     particolarmente
    -1.05
     infatti
    -1.04
     impieg
    -1.03
     leggermente
    -1.03
    immediately
    -1.03
    minated
    -1.01
    siamo
    -1.01
    POSITIVE LOGITS
     lastly
    3.11
     Lastly
    2.95
     finally
    2.83
    Lastly
    2.75
     Finally
    2.59
    Finally
    2.34
     enfin
    2.33
     finalmente
    2.23
     наконец
    2.20
     infine
    2.16
    Activations Density 0.052%

    No Known Activations