© 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. 66852
    Prev
    Next
    INDEX
    Explanations

    programs, trips, awards, spotlights

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

    The neuron detects numeric expressions—tokens that are numbers or figures (including decimals) in the 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
    engaruhi
    -0.93
     MODER
    -0.93
     LEAF
    -0.91
     Deixe
    -0.91
    ftar
    -0.90
    を作って
    -0.90
     THOR
    -0.87
    读
    -0.87
     MONITOR
    -0.85
    آیا
    -0.85
    POSITIVE LOGITS
     by
    1.19
     who
    1.04
     were
    0.99
     there
    0.98
     those
    0.98
    選ば
    0.97
     veteran
    0.95
     from
    0.94
    0.93
    Three
    0.88
    Activations Density 0.029%

    No Known Activations