© 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. 35267
    Prev
    Next
    INDEX
    Explanations

    names, words, and abbreviations

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

    The neuron activates on numeric tokens (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
    MANUEL
    -0.91
     nõ
    -0.85
    ilitas
    -0.85
    钳
    -0.83
     congruent
    -0.83
    Nolan
    -0.80
    医药
    -0.78
    Domains
    -0.78
     tõ
    -0.78
     разных
    -0.77
    POSITIVE LOGITS
     name
    1.47
     plural
    1.42
     term
    1.38
     word
    1.14
    称
    1.09
     acronym
    1.08
     abbreviation
    1.07
     Bezeichnung
    1.03
     phrase
    1.00
     शब्द
    0.99
    Activations Density 0.057%

    No Known Activations