© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54224
    Prev
    Next
    INDEX
    Explanations

    adding to lists or variables

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

    The neuron activates on numeric literals (digits or numbers) in code.

    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
    rfan
    -1.01
    wanna
    -0.98
     deine
    -0.96
     puisqu
    -0.94
     realmente
    -0.93
    weren
    -0.92
    mme
    -0.92
    lana
    -0.91
    tsd
    -0.90
    绷
    -0.89
    POSITIVE LOGITS
     from
    1.05
     before
    1.04
     μπορεί
    0.95
     while
    0.92
     could
    0.92
     it
    0.92
    Хотя
    0.91
    BeforeMethod
    0.91
    hmigung
    0.90
    商人
    0.89
    Activations Density 0.012%

    No Known Activations