© 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. 69034
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron is primarily detecting numeric literals (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
    necessarily
    -1.23
    não
    -1.18
    peut
    -1.17
     ALREADY
    -1.16
    쨩
    -1.16
     rú
    -1.12
    羮
    -1.12
     Não
    -1.11
     Ý
    -1.10
     cinquième
    -1.10
    POSITIVE LOGITS
     another
    1.32
     also
    1.22
     more
    1.22
     use
    1.12
     new
    1.12
     it
    1.12
     other
    1.11
     change
    1.04
     areas
    1.03
     further
    1.02
    Activations Density 0.010%

    No Known Activations