© 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. 112643
    Prev
    Next
    INDEX
    Explanations

    quantities ("lot of", "more", "some")

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

    The neuron spikes on words expressing large or comparative quantities (e.g. “lot,” “more,” “much,” “stuff”).

    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
    
    -2.06
    塒
    -2.06
    逦
    -2.06
    鸶
    -2.05
     itſelf
    -2.03
    ſſel
    -1.99
    鸱
    -1.98
    𓆜
    -1.97
    ſem
    -1.95
    疍
    -1.95
    POSITIVE LOGITS
    </strong>
    1.94
     AND
    1.92
     $
    1.91
     been
    1.84
     diferente
    1.81
    。"
    1.80
     \&
    1.77
     
    1.73
     और
    1.70
     свою
    1.70
    Activations Density 0.063%

    No Known Activations