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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110601
    Prev
    Next
    INDEX
    Explanations

    second highest, 12th populated, top 10

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

    The neuron is detecting numerical expressions—especially ordinals and statistical figures indicating rank or magnitude.

    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
     abſ
    -1.30
    ᠌
    -1.24
    完全
    -1.18
    angkutan
    -1.16
     the
    -1.15
     geniales
    -1.15
     atletas
    -1.13
     a
    -1.13
     &___
    -1.11
     quoque
    -1.10
    POSITIVE LOGITS
     with
    1.87
    両方
    1.35
     Both
    1.22
    质感
    1.13
    Soorten
    1.13
    这么多
    1.13
     people
    1.12
     primarily
    1.09
     sowohl
    1.08
     came
    1.07
    Activations Density 0.150%

    No Known Activations