© 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. 22-GEMMASCOPE-RES-131K
    7. 68557
    Prev
    Next
    INDEX
    Explanations

    largest, second, fourthlargest, fourteenth

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

    The neuron activates on tokens conveying quantitative or ranking information—numbers, ordinals, and superlative descriptors (e.g. “largest,” “first,” “one,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    >--}}
    -0.96
    Those
    -0.95
     Algunos
    -0.94
     Incluye
    -0.90
     Incluso
    -0.89
    雋
    -0.85
     deswegen
    -0.85
    Incluye
    -0.85
    تيجة
    -0.84
     praktischen
    -0.84
    POSITIVE LOGITS
     worldwide
    1.09
     its
    1.07
     other
    0.98
     peniten
    0.93
     Atem
    0.90
     national
    0.90
     part
    0.89
     cincin
    0.89
     mariana
    0.88
     destina
    0.88
    Activations Density 0.092%

    No Known Activations