© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3469
    Prev
    Next
    INDEX
    Explanations

    legal cases and court decisions

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

    The neuron detects numeric portions of formal citations (e.g. volume and reporter page numbers in legal references).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccountNumber
    0.72
    تان
    0.70
    
    0.68
     $=$
    0.67
    אַ
    0.66
    :
    0.66
    <0x80>
    0.64
     posibilidad
    0.64
     テ
    0.64
     あなた
    0.64
    POSITIVE LOGITS
     lessening
    0.76
     stabile
    0.68
     abol
    0.65
     softens
    0.65
     commerciales
    0.64
    RELATIVA
    0.64
    FEDERAL
    0.64
    自从
    0.64
    ctrine
    0.63
     softening
    0.63
    Activations Density 0.001%

    No Known Activations