© 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. 130276
    Prev
    Next
    INDEX
    Explanations

    music and sports news

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

    The neuron detects punctuation marks—especially commas and periods.

    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
    }}_
    -1.61
    ｅ
    -1.59
    ”),
    -1.59
     people
    -1.52
    ā
    -1.49
    されます
    -1.47
    sqm
    -1.47
    ｙ
    -1.46
    🤤
    -1.46
     otros
    -1.44
    POSITIVE LOGITS
     unités
    1.70
     سينما
    1.54
    盉
    1.47
    可能会
    1.45
     potrebbe
    1.45
     beleid
    1.39
    即将
    1.38
    <i>
    1.38
     —
    1.37
    cloudf
    1.35
    Activations Density 0.111%

    No Known Activations