© 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. 87078
    Prev
    Next
    INDEX
    Explanations

    quantifiers followed by descriptions

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

    The neuron activates on multi-digit numeric tokens (written numbers), flagging explicit large numerical values 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_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
     salonu
    -1.64
    ܆
    -1.38
    laria
    -1.38
    絝
    -1.35
     dekol
    -1.34
    xvii
    -1.34
     bluz
    -1.32
     hisz
    -1.31
     всички
    -1.30
     baterie
    -1.29
    POSITIVE LOGITS
     of
    3.45
     had
    2.31
     is
    2.30
     are
    2.27
     have
    2.19
     has
    2.14
     was
    2.05
     them
    1.95
     ones
    1.90
     will
    1.69
    Activations Density 0.088%

    No Known Activations