© 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. 40151
    Prev
    Next
    INDEX
    Explanations

    corresponds to

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

    The neuron activates on numeric tokens—especially decimal or integer measurements (e.g. “150,” “86.5,” “142”)—i.e. it finds 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
     Namun
    -2.22
     Meski
    -1.95
    😒
    -1.88
    😟
    -1.88
    ！"
    -1.86
     Hingga
    -1.84
    😯
    -1.84
     وہ
    -1.84
    😰
    -1.84
    cún
    -1.80
    POSITIVE LOGITS
    衚
    2.53
    余談
    2.06
    スム
    2.02
     It
    1.91
    両方
    1.91
    儅
    1.90
     you
    1.88
    一起来
    1.87
    次回は
    1.86
     bluntly
    1.83
    Activations Density 0.016%

    No Known Activations