© 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. 34-GEMMASCOPE-RES-131K
    7. 117243
    Prev
    Next
    INDEX
    Explanations

    Sigma-Aldrich company names

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

    The neuron strongly activates on numerical tokens (digits) 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_34/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
    증
    -0.82
     编辑
    -0.80
     作者
    -0.79
    ailer
    -0.79
    ₁(
    -0.77
    ยิ่ง
    -0.77
    PERT
    -0.75
     về
    -0.73
    arkov
    -0.73
     jailed
    -0.72
    POSITIVE LOGITS
     Sigma
    2.20
    Sigma
    1.98
     sigma
    1.59
    sigma
    1.47
     Aldrich
    1.32
    SIGMA
    1.12
     SIG
    1.11
     Invit
    1.11
     Fisher
    1.04
    Aldrich
    1.04
    Activations Density 0.055%

    No Known Activations