© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7060
    Prev
    Next
    INDEX
    Explanations

    quantities and counts

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

    The main thing this neuron does is detect numeric quantities (digits 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_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
     that
    -1.91
     they
    -1.57
     in
    -1.55
     just
    -1.52
     after
    -1.52
     even
    -1.43
    许久
    -1.38
     during
    -1.31
     their
    -1.27
     simply
    -1.24
    POSITIVE LOGITS
     évolution
    1.30
    :{
    1.29
    ása
    1.25
    хео
    1.23
    rified
    1.22
    itzende
    1.21
     Siapa
    1.20
    糁
    1.19
    сар
    1.19
    geführt
    1.19
    Activations Density 0.077%

    No Known Activations