© 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. 34663
    Prev
    Next
    INDEX
    Explanations

    punctuation and case separation

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

    The neuron fires on numeric tokens—i.e. it detects numbers or numeric sequences (digits, coordinates, measurements) embedded in code or data strings.

    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
     in
    -1.13
    🌻
    -1.13
     Vecchio
    -1.07
    🌼
    -1.05
    💓
    -1.05
     Those
    -1.04
     during
    -1.04
     striving
    -1.02
    ométrique
    -1.02
    💀
    -1.02
    POSITIVE LOGITS
     verschillende
    1.26
     goofy
    1.16
     afuera
    1.13
     lauded
    1.11
     strikingly
    1.10
     trám
    1.09
     verschiedenen
    1.09
     amazingly
    1.08
     ridiculously
    1.08
     diversos
    1.07
    Activations Density 0.001%

    No Known Activations