© 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. 35697
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

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

    The neuron consistently activates on tokens that are the two-character punctuation sequence “.,” (a comma immediately followed by a period).

    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
    檍
    -2.03
    龊
    -1.90
     name
    -1.90
    賤
    -1.88
     zweite
    -1.86
    籬
    -1.84
    屜
    -1.83
    ൎ
    -1.81
     waning
    -1.80
     [];
    -1.78
    POSITIVE LOGITS
     builds
    2.45
    te
    2.38
    re
    2.28
    𖣘
    2.16
    他
    2.16
    –
    2.11
     reveals
    2.08
    se
    2.08
    </h1>
    2.05
    ي
    2.03
    Activations Density 0.049%

    No Known Activations