© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129902
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly responsive to numeric tokens, i.e., written numbers or digit sequences in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    health issues and symptoms

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

    narratives describing medical symptoms, health issues, or physical conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     such
    -1.15
    Ṡ
    -1.03
    衛隊
    -0.95
     ۲۵
    -0.94
    such
    -0.92
    成功
    -0.90
    讐
    -0.89
    从而
    -0.88
     tandis
    -0.88
     will
    -0.88
    POSITIVE LOGITS
     symptoms
    1.69
     Symptoms
    1.33
    nehå
    1.27
     intuition
    1.21
     Kiedy
    1.20
    Pozdrawiam
    1.20
     sports
    1.20
     signs
    1.18
    trường
    1.17
     alarming
    1.16
    Activations Density 0.061%

    No Known Activations