© 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. 73826
    Prev
    Next
    INDEX
    Explanations

    code include and import statements

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

    The neuron detects integer numeric tokens (i.e. standalone numbers) in code or 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
     zví
    -1.03
     radiador
    -1.02
     rekom
    -1.01
     klock
    -1.01
    cookieParser
    -1.00
    reportError
    -1.00
    lessons
    -0.99
    ᗨ
    -0.99
    ovým
    -0.98
     জন
    -0.96
    POSITIVE LOGITS
     will
    1.20
     после
    1.20
     primero
    1.11
     setup
    1.08
     first
    1.07
     everything
    1.05
     medica
    1.03
     after
    1.00
     mentally
    0.99
     вместо
    0.98
    Activations Density 0.001%

    No Known Activations