© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49225
    Prev
    Next
    INDEX
    Explanations

    on UNITED STATES COURT

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

    The neuron strongly activates on closing quotation marks immediately followed by commas (e.g. '",'), i.e. the ends of quoted strings in data/JSON-style syntax.

    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
     on
    -0.93
    зки
    -0.90
     dormant
    -0.81
    ဒ
    -0.79
     at
    -0.76
     wraz
    -0.75
    entir
    -0.75
    vų
    -0.74
     Pflanze
    -0.74
     coincides
    -0.73
    POSITIVE LOGITS
    鎰
    0.95
    0.89
    ^{*}\
    0.88
     케
    0.86
                           
    0.86
    ’
    0.86
     tranches
    0.85
     Magician
    0.84
    itemize
    0.84
     Evangelist
    0.82
    Activations Density 0.001%

    No Known Activations