© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57546
    Prev
    Next
    INDEX
    Explanations

    starts with quotes

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

    The neuron detects typographic single‐quote/apostrophe characters (curly ’ and ‘) in the 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_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
    since
    -0.87
    匂
    -0.86
     TÉCNICA
    -0.85
    because
    -0.84
    起码
    -0.83
     since
    -0.81
     closes
    -0.80
     mainly
    -0.80
     хорошем
    -0.79
    ManagedBean
    -0.79
    POSITIVE LOGITS
    Tis
    1.43
    Twas
    1.25
    ’
    1.02
     lèvres
    0.99
     sababu
    0.94
    TIS
    0.94
     Tis
    0.93
    backdrop
    0.91
    twas
    0.90
     sélectionnés
    0.88
    Activations Density 0.003%

    No Known Activations