© 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. 127677
    Prev
    Next
    INDEX
    Explanations

    minimums and maximums

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

    The neuron activates on numeric expressions and measurements (e.g. minimums, maximums, decimal values, and other quantities).

    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
    いま
    -1.53
     detayl
    -1.52
    iſter
    -1.52
    になっている
    -1.47
    "",
    -1.46
    栳
    -1.42
     ¿
    -1.40
     The
    -1.38
     stuks
    -1.38
     нашу
    -1.37
    POSITIVE LOGITS
    You
    1.57
    To
    1.53
    With
    1.45
     哪些
    1.45
    when
    1.41
    觔
    1.41
     科技
    1.38
     is
    1.38
     意思
    1.38
    most
    1.35
    Activations Density 0.015%

    No Known Activations