© 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. 47454
    Prev
    Next
    INDEX
    Explanations

    section titles or code snippets

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

    The neuron fires on numeric tokens—especially version numbers, package versions, citation numbers, etc.

    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
     of
    -2.39
     by
    -1.56
     albeit
    -1.45
    7
    -1.45
    re
    -1.45
    または
    -1.44
    9
    -1.41
    _
    -1.40
     at
    -1.35
     (
    -1.34
    POSITIVE LOGITS
     havet
    1.58
     helpt
    1.49
     Duitsland
    1.38
    ussure
    1.38
     itd
    1.36
    iços
    1.34
     escribiendo
    1.34
     comiendo
    1.34
    álise
    1.33
     indep
    1.31
    Activations Density 0.044%

    No Known Activations