© 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. 70867
    Prev
    Next
    INDEX
    Explanations

    proper execution and suitability

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

    The neuron strongly activates on numeric tokens—especially measurements or quantities expressed as numbers (often with decimals).

    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
     because
    -1.38
     whether
    -1.36
     whatever
    -1.34
     потому
    -1.33
     since
    -1.30
    whatever
    -1.17
     étant
    -1.17
    noted
    -1.15
     omdat
    -1.13
     vielen
    -1.12
    POSITIVE LOGITS
     peligroso
    1.40
     inimigo
    1.32
     chcesz
    1.27
     situaciones
    1.25
     Gesetze
    1.23
    лив
    1.22
     أيضًا
    1.21
     rosto
    1.20
     Jangan
    1.20
     Also
    1.18
    Activations Density 0.047%

    No Known Activations