© 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. 34-GEMMASCOPE-RES-131K
    7. 116571
    Prev
    Next
    INDEX
    Explanations

    Q: ; Hip Stuff Mater Daily

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

    The neuron is primarily detecting semicolon tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     seemed
    -0.84
     been
    -0.84
     dadas
    -0.81
     BehaviorSubject
    -0.80
     preponderance
    -0.78
     meticulously
    -0.77
     Konkur
    -0.76
    亲爱的
    -0.75
    フード
    -0.75
     seemingly
    -0.74
    POSITIVE LOGITS
     através
    0.83
     tên
    0.82
    ilding
    0.81
     ainsi
    0.80
    nin
    0.79
    ргани
    0.78
     CLS
    0.78
    essment
    0.78
     OHIO
    0.77
    así
    0.76
    Activations Density 0.000%

    No Known Activations