© 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. 79520
    Prev
    Next
    INDEX
    Explanations

    describing states or comparisons

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

    This neuron detects numeric tokens and numeric expressions (e.g., integers, decimals, and numbers in 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
    是怎么回事
    -0.99
    ıyors
    -0.92
    ğına
    -0.90
     باشی
    -0.88
    Ẓ
    -0.87
    ències
    -0.87
     læ
    -0.87
    částí
    -0.86
     dře
    -0.85
     balení
    -0.85
    POSITIVE LOGITS
     is
    2.02
     will
    1.64
     would
    1.54
     could
    1.41
     may
    1.38
     can
    1.31
     might
    1.30
     was
    1.27
     isn
    1.21
     should
    1.16
    Activations Density 0.165%

    No Known Activations