© 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. 10-GEMMASCOPE-RES-131K
    7. 72699
    Prev
    Next
    INDEX
    Explanations

    L. names

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

    The neuron detects legal citation markers, particularly reporter abbreviations like “L.” followed by volume or 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
    茘
    -3.19
    
    -2.70
    Typically
    -2.66
    釙
    -2.63
    
    -2.55
    Donativos
    -2.36
    緜
    -2.36
    Usually
    -2.33
    蝙
    -2.31
    玧
    -2.31
    POSITIVE LOGITS
    睺
    2.56
    also
    2.23
    也会
    2.20
    \
    2.19
    身影
    2.19
    蒹
    2.16
     have
    2.14
    殽
    2.13
    蠖
    2.13
     THOSE
    2.09
    Activations Density 0.017%

    No Known Activations