© 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. 75376
    Prev
    Next
    INDEX
    Explanations

    court citations and legal references

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

    This neuron detects the volume numbers (and associated markers like asterisks) used in legal case citation references.

    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
     with
    -1.54
     all
    -1.52
     in
    -1.40
     After
    -1.36
     after
    -1.36
     if
    -1.30
     including
    -1.30
     mostly
    -1.29
     using
    -1.29
     Even
    -1.27
    POSITIVE LOGITS
    あー
    1.27
    すっ
    1.25
     sooo
    1.20
     london
    1.15
     soooo
    1.11
    えっ
    1.08
     zoude
    1.07
     magnific
    1.06
    あぁ
    1.06
     verborgen
    1.05
    Activations Density 0.014%

    No Known Activations