© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102160
    Prev
    Next
    INDEX
    Explanations

    describing types of treatments

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

    medical and therapeutic treatment descriptions, especially related to massage, acupuncture, and spa services.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The main thing this neuron does is spot numeric expressions and measurement details (e.g. hours, course lengths, dosages, counts).

    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
     like
    -1.52
    ּוֹ
    -1.37
     Those
    -1.23
     to
    -1.22
    variations
    -1.19
    וֹ
    -1.17
     these
    -1.16
     some
    -1.16
     this
    -1.16
    を選択します
    -1.15
    POSITIVE LOGITS
    ׇ
    1.55
     ویتامین
    1.41
    før
    1.36
    ----</
    1.34
    ֺ
    1.33
    balleur
    1.27
    zyć
    1.25
    цький
    1.25
    IDEOGRAPH
    1.24
    塁
    1.23
    Activations Density 0.103%

    No Known Activations