© 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. 66199
    Prev
    Next
    INDEX
    Explanations

    hypothetical conditions and outcomes

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

    The main thing this neuron does is detect multi-digit numeric tokens (large numbers or percentages) 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
     bahwa
    -1.09
    Когда
    -1.09
    多个
    -1.07
    yourself
    -1.02
    lín
    -1.02
    átor
    -0.99
    графія
    -0.97
    tled
    -0.96
    DataURL
    -0.96
     bahawa
    -0.95
    POSITIVE LOGITS
     would
    2.20
     if
    1.48
     gdyby
    1.16
     this
    1.13
    だけで
    1.11
    だったら
    1.09
     olisi
    1.09
     every
    1.09
     could
    1.09
     wouldn
    1.08
    Activations Density 0.039%

    No Known Activations