© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58486
    Prev
    Next
    INDEX
    Explanations

    legal citations and addresses

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

    This neuron detects the volume numbers in legal case citations (the multi-digit numbers that precede reporter abbreviations).

    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
     really
    -1.43
     this
    -1.33
     some
    -1.32
     so
    -1.32
     what
    -1.27
     make
    -1.25
     very
    -1.25
     had
    -1.23
     takes
    -1.22
     incredible
    -1.22
    POSITIVE LOGITS
     flamboyant
    1.27
     opulent
    1.27
     ornate
    1.22
     MAKING
    1.20
     alluring
    1.19
     GETTING
    1.18
    姈
    1.16
     tumultuous
    1.15
     DIDN
    1.14
     masterful
    1.14
    Activations Density 0.083%

    No Known Activations