© 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. 86794
    Prev
    Next
    INDEX
    Explanations

    punctuations followed by words

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

    The neuron is a detector for quotation marks and the boundaries of quoted speech.

    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
     tačiau
    -1.20
    
    -1.09
     nepiecieš
    -1.09
    прочем
    -1.08
    eapples
    -1.07
     BSEB
    -1.03
     "",
    -1.03
     wenigstens
    -1.01
    之色
    -0.99
    かわらず
    -0.98
    POSITIVE LOGITS
     there
    2.56
     it
    2.41
     you
    2.16
     that
    2.02
     people
    1.97
     we
    1.95
     our
    1.74
     when
    1.73
     what
    1.65
     if
    1.63
    Activations Density 0.015%

    No Known Activations