© 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. 10-GEMMASCOPE-RES-131K
    7. 58428
    Prev
    Next
    INDEX
    Explanations

    JSON keys and values

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

    This neuron fires on JSON-style response field names (e.g. “success,” “status,” “error,” “count,” “result”) in code or data snippets.

    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
     rempli
    -1.59
    栒
    -1.55
    </h3>
    -1.44
    嫘
    -1.41
     บาท
    -1.41
    ayage
    -1.37
    🧌
    -1.37
    艄
    -1.36
     różne
    -1.35
    癭
    -1.35
    POSITIVE LOGITS
     only
    1.84
     just
    1.67
    </b>
    1.66
     "
    1.58
    "
    1.38
     more
    1.38
     at
    1.36
     could
    1.34
    _
    1.32
     this
    1.31
    Activations Density 0.009%

    No Known Activations