© 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. 34-GEMMASCOPE-RES-131K
    7. 53870
    Prev
    Next
    INDEX
    Explanations

    numbers followed by thousands

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

    The neuron fires on long runs of digit tokens (especially multi‐digit numeric amounts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     also
    -1.34
    ),
    -1.09
     that
    -1.04
     why
    -0.93
     również
    -0.92
    ));
    -0.91
     now
    -0.89
     will
    -0.89
    ",
    -0.89
    Törté
    -0.88
    POSITIVE LOGITS
     هزار
    1.38
     thousand
    1.34
     milliers
    1.31
    0
    1.16
     thousands
    1.04
    Thousands
    0.98
     ألف
    0.96
     тыся
    0.93
    thou
    0.91
    万
    0.91
    Activations Density 0.114%

    No Known Activations