© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    among the groups

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

    The neuron specifically fires on standalone numerals (counts or measurements) in the text, such as sample‐size figures.

    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
            
    -2.14
    âmara
    -1.89
     award
    -1.87
     navegando
    -1.81
     zijn
    -1.81
     suficientemente
    -1.79
     ezt
    -1.77
    たまた
    -1.77
    荻
    -1.74
    ⩴
    -1.74
    POSITIVE LOGITS
     are
    2.27
    s
    2.17
    寕
    2.08
    ৄ
    2.06
    郇
    1.89
    st
    1.89
     所以
    1.86
    蕯
    1.86
    MenuInflater
    1.82
    賔
    1.82
    Activations Density 0.015%

    No Known Activations