© 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. 53962
    Prev
    Next
    INDEX
    Explanations

    license, antigen, ship

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

    This neuron is strongly activated by tokens containing digits (e.g. numeric literals, version numbers, dates, or otherwise digit-heavy tokens).

    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
    Meditation
    -0.72
    Waist
    -0.71
    ilh
    -0.68
    きます
    -0.66
    铖
    -0.66
    Passer
    -0.65
    rira
    -0.65
    Moral
    -0.64
     Solidarity
    -0.64
     prospectus
    -0.63
    POSITIVE LOGITS
     JComboBox
    0.78
    Business
    0.73
     fale
    0.71
    URLConnection
    0.70
    IB
    0.68
     cyclic
    0.68
     mondo
    0.67
    ź
    0.67
    бри
    0.67
     реакции
    0.66
    Activations Density 0.089%

    No Known Activations