© 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. 66434
    Prev
    Next
    INDEX
    Explanations

    legal, scientific, or factual contexts

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

    The neuron fires strongly on formal legal and contractual terminology (e.g. contract, renewed, consent, mortgage, subsequent mortgage debt).

    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
     coloriage
    -1.68
     formid
    -1.59
     corriger
    -1.55
     groote
    -1.55
     maille
    -1.51
     paillettes
    -1.51
     heilig
    -1.48
     extrêmement
    -1.48
     bijoux
    -1.46
     acrescent
    -1.45
    POSITIVE LOGITS
     or
    2.53
     any
    2.11
     before
    2.08
     when
    2.00
     if
    1.97
     may
    1.91
     only
    1.88
     even
    1.86
     can
    1.84
     after
    1.83
    Activations Density 0.019%

    No Known Activations