© 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. 127380
    Prev
    Next
    INDEX
    Explanations

    quoted text

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

    This neuron detects opening quotation marks (i.e. the start of quoted text).

    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
     to
    -1.84
     the
    -1.66
     for
    -1.59
    only
    -1.55
     unless
    -1.48
     it
    -1.46
    身边的
    -1.45
     instead
    -1.45
     only
    -1.43
    </b>
    -1.38
    POSITIVE LOGITS
     redan
    1.83
     berättar
    1.63
     där
    1.63
    nitř
    1.61
     svårt
    1.60
    irmingham
    1.59
     möjligt
    1.58
     klubben
    1.58
    鋮
    1.56
     afectados
    1.55
    Activations Density 0.101%

    No Known Activations