© 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. 87290
    Prev
    Next
    INDEX
    Explanations

    F.2d citations

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

    The neuron fires on the volume numbers in legal case citations (the digit(s) immediately preceding the reporter abbreviation, e.g. the “5” in “5 F.2d”).

    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
    ztes
    -2.03
     giras
    -2.02
     llorar
    -1.84
    
    -1.81
    热的
    -1.81
     perdón
    -1.80
     rompi
    -1.80
     pestañas
    -1.79
     direito
    -1.77
     músicos
    -1.76
    POSITIVE LOGITS
    ’
    2.67
    </h3>
    2.36
    ]
    2.09
    *
    1.96
    \
    1.95
    an
    1.86
    .”
    1.83
    更何况
    1.82
    ,“
    1.80
    .’’
    1.79
    Activations Density 0.026%

    No Known Activations