© 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. 44405
    Prev
    Next
    INDEX
    Explanations

    to show that

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

    The neuron responds to numeric tokens (numbers, including those with decimal points) 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
     where
    -1.54
    ią
    -1.40
     fungerer
    -1.35
     limba
    -1.34
    rigkeit
    -1.34
    Azur
    -1.31
     variar
    -1.28
    ropractic
    -1.27
    órica
    -1.26
     precisam
    -1.26
    POSITIVE LOGITS
     of
    2.00
     Și
    1.39
     [
    1.39
    ].
    1.33
     Vorgang
    1.31
    也得
    1.30
     Acest
    1.28
     Dacă
    1.27
     between
    1.27
     are
    1.27
    Activations Density 0.048%

    No Known Activations