© 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. 115534
    Prev
    Next
    INDEX
    Explanations

    time frequency units

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

    The neuron strongly activates on tokens containing digits—i.e. numeric literals 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_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
     corrupted
    -0.76
    孪
    -0.75
    inado
    -0.73
     puberty
    -0.73
     ALC
    -0.73
     reformer
    -0.72
    洙
    -0.72
     Hedgehog
    -0.71
    火山
    -0.71
     clinica
    -0.70
    POSITIVE LOGITS
     frequency
    1.59
    frequency
    1.47
    Frequency
    1.42
     Frequency
    1.38
     frequencies
    1.38
     freq
    1.30
     frecuencia
    1.23
    freq
    1.22
     frequenza
    1.13
     FREQUENCY
    1.09
    Activations Density 0.032%

    No Known Activations