© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 74991
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptors

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

    The neuron is specifically triggered by numeric tokens—i.e. it finds numbers and measurements 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_22/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
     helped
    -1.52
     allows
    -1.52
     will
    -1.50
     became
    -1.47
     showed
    -1.45
     what
    -1.44
     or
    -1.42
     aspects
    -1.41
     receive
    -1.36
     their
    -1.29
    POSITIVE LOGITS
     of
    3.44
     cuma
    1.41
    soit
    1.38
    蕖
    1.38
     Presidencia
    1.36
     verdo
    1.35
     siè
    1.34
     apparaissent
    1.33
     obſ
    1.31
     viennent
    1.30
    Activations Density 0.059%

    No Known Activations