© 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. 10-GEMMASCOPE-RES-131K
    7. 61278
    Prev
    Next
    INDEX
    Explanations

    legal citation numbers

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

    This neuron detects numeric tokens used in legal case citations (volume and page 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_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
     kaikk
    -1.45
     yrity
    -1.44
    verarbeitung
    -1.42
     guapos
    -1.42
     сына
    -1.42
     любые
    -1.40
    撹
    -1.38
    /
    -1.38
     vingt
    -1.36
     säs
    -1.36
    POSITIVE LOGITS
     it
    1.90
     after
    1.72
     chose
    1.69
     from
    1.64
     creating
    1.60
     our
    1.60
     making
    1.59
     with
    1.57
     came
    1.53
     незавер
    1.53
    Activations Density 0.032%

    No Known Activations