© 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. 10-GEMMASCOPE-RES-131K
    7. 68829
    Prev
    Next
    INDEX
    Explanations

    tokens after commas

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

    This neuron responds to comma tokens in code, highlighting each comma.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Then
    -1.62
    ⿻
    -1.56
    izó
    -1.53
    of
    -1.41
     At
    -1.41
    ba
    -1.41
    ytä
    -1.40
     indulgent
    -1.40
    ke
    -1.37
    ität
    -1.36
    POSITIVE LOGITS
    }
    1.73
     blanda
    1.68
     ausgeführt
    1.63
     vermittelt
    1.61
     MUCH
    1.61
     affords
    1.59
     länger
    1.57
     erlaubt
    1.56
    訁
    1.55
    doesn
    1.54
    Activations Density 0.007%

    No Known Activations