© 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. 57522
    Prev
    Next
    INDEX
    Explanations

    get a before noun

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

    The neuron fires on numeric tokens—i.e. numbers (like monetary amounts, percentages, counts) in the text.

    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
    on
    -2.67
    s
    -2.41
    these
    -2.31
    𓋼
    -2.25
    僂
    -2.25
    婓
    -2.25
    It
    -2.22
    夀
    -2.08
    鯓
    -2.03
    of
    -1.95
    POSITIVE LOGITS
     rid
    2.59
    鵟
    2.02
    ໊
    1.95
     eer
    1.81
    
    1.80
     ofere
    1.77
     hold
    1.74
    襞
    1.72
     возможность
    1.65
    弖
    1.63
    Activations Density 0.025%

    No Known Activations