© 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. 129594
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find numeric measurements (numbers and quantified values) in the text.

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

    environments and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     aksesuar
    -1.16
     rendement
    -1.15
    onekana
    -1.13
     Inſ
    -1.09
     INSPECTION
    -1.07
     résultat
    -1.05
    Дорогие
    -1.01
    Judas
    -1.00
     côtes
    -0.99
    monary
    -0.97
    POSITIVE LOGITS
     environments
    1.41
     conditions
    1.40
     environment
    1.32
     changes
    1.30
     time
    1.20
     for
    1.19
     temperatures
    1.16
     ambient
    1.13
     changed
    1.12
     īpa
    1.11
    Activations Density 0.117%

    No Known Activations