© 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. 54538
    Prev
    Next
    INDEX
    Explanations

    citations and court references

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

    The neuron detects numeric tokens used in legal citations—particularly volume and page numbers (and related footnote markers).

    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
     by
    -1.34
     in
    -1.23
    While
    -1.17
    Since
    -1.09
    This
    -1.09
    Some
    -1.08
    Now
    -1.02
     While
    -1.02
     now
    -1.01
    ínica
    -1.01
    POSITIVE LOGITS
     amenaz
    1.22
     detayl
    1.15
     sujetos
    1.14
     čern
    1.13
    CastException
    1.12
     malzeme
    1.10
     świąte
    1.09
     sitesinde
    1.09
    ologic
    1.05
     hermosos
    1.05
    Activations Density 0.018%

    No Known Activations