© 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. 22-GEMMASCOPE-RES-131K
    7. 71665
    Prev
    Next
    INDEX
    Explanations

    json and code structures

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

    The neuron fires on JSON property names (i.e. the keys in JSON‐style objects).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    eseen
    -1.11
    imee
    -1.03
    imod
    -1.02
    SPECIAL
    -1.01
    ylated
    -0.96
    balar
    -0.95
     AVAILABLE
    -0.95
    ĝ
    -0.94
    Find
    -0.94
    튿
    -0.94
    POSITIVE LOGITS
     two
    1.10
     such
    1.05
     including
    0.98
     consisting
    0.96
    それでは
    0.96
    liger
    0.94
    曲は
    0.94
     vzd
    0.93
    ！！！！
    0.92
     вместо
    0.91
    Activations Density 0.026%

    No Known Activations