© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15130
    Prev
    Next
    INDEX
    Explanations

    {

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

    The neuron specializes in spotting numerical expressions (integers or decimals) 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
     "
    -1.57
     "...
    -1.48
     sehr
    -1.27
     Certificado
    -1.22
    Очень
    -1.21
    屋の
    -1.20
    Last
    -1.20
    Very
    -1.16
     certificado
    -1.14
     ("
    -1.13
    POSITIVE LOGITS
     of
    1.60
     that
    1.53
     only
    1.48
     andata
    1.40
     its
    1.35
    </em>
    1.32
    </h2>
    1.31
     μόνο
    1.30
    良いです
    1.30
    >");
    1.26
    Activations Density 0.127%

    No Known Activations