© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27042
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and words

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

    The neuron fires on numeric tokens (i.e. multi‐digit numbers) 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_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
    ího
    -1.18
     this
    -1.16
     conseguido
    -1.13
     alfombra
    -1.07
     возрасте
    -1.04
    więks
    -1.03
     bebé
    -1.03
    CROSSTALK
    -1.02
    存知
    -1.02
     būt
    -1.02
    POSITIVE LOGITS
     פשוט
    0.99
     можно
    0.94
     einfach
    0.91
    竄
    0.91
     etc
    0.87
     просто
    0.86
     только
    0.83
     Similarly
    0.82
    (/^
    0.81
    ㄴ
    0.81
    Activations Density 0.066%

    No Known Activations