© 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. 14848
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation separators

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

    The neuron fires on standalone numeric tokens (i.e. 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_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
     SwiftUI
    -1.11
    EREN
    -1.09
     décide
    -1.03
    栳
    -1.01
     gorra
    -1.00
     Schöne
    -1.00
     officiers
    -1.00
    ילום
    -0.98
     issus
    -0.98
    ఱ
    -0.98
    POSITIVE LOGITS
     has
    1.13
     product
    1.13
     contains
    1.05
     гото
    1.05
    貶
    1.03
     which
    1.02
     may
    1.01
    儼
    0.98
    ifoli
    0.96
     but
    0.95
    Activations Density 0.000%

    No Known Activations