© 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. 34-GEMMASCOPE-RES-131K
    7. 91157
    Prev
    Next
    INDEX
    Explanations

    numbers followed by opening parenthesis

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

    The neuron detects numeric sequences that are part of legal case citations (e.g. volume, page, and parenthetical year numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    عادة
    -0.82
    }{{
    -0.82
    miljø
    -0.80
    \#:
    -0.79
     forgotten
    -0.78
    aspectj
    -0.75
     örgü
    -0.74
    Appellant
    -0.74
     práticas
    -0.73
    ）（
    -0.72
    POSITIVE LOGITS
     abond
    1.00
    RIN
    0.83
    recently
    0.83
     Annotation
    0.78
     ModelRenderer
    0.78
     remonter
    0.76
     RTE
    0.76
     dissenting
    0.75
    зидент
    0.75
     où
    0.74
    Activations Density 0.093%

    No Known Activations