© 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. 10-GEMMASCOPE-RES-131K
    7. 65412
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron is triggered by numeric tokens containing a decimal point (i.e. floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     and
    -2.39
     in
    -2.02
     the
    -1.97
     by
    -1.93
     with
    -1.88
     including
    -1.79
     some
    -1.77
     at
    -1.74
     a
    -1.73
     (
    -1.67
    POSITIVE LOGITS
    MERS
    1.75
    HING
    1.70
     interni
    1.68
    ANZE
    1.68
    нера
    1.67
    秶
    1.59
    КИ
    1.55
     refuser
    1.55
     pylori
    1.55
     emporter
    1.55
    Activations Density 0.063%

    No Known Activations