© 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. 22-GEMMASCOPE-RES-131K
    7. 33342
    Prev
    Next
    INDEX
    Explanations

    artists, such, three, being, slated

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

    The neuron is triggered by numeric expressions and measurements (e.g. digits, units like “miles”) 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_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
     jaja
    -1.48
    😡
    -1.45
    letics
    -1.40
    😴
    -1.38
    Pinterest
    -1.30
    ternut
    -1.29
     jaj
    -1.29
    CDN
    -1.26
    
    -1.26
    👎
    -1.25
    POSITIVE LOGITS
     here
    1.25
     kinda
    1.23
     people
    1.20
     got
    1.18
     didn
    1.17
     like
    1.17
     gotta
    1.17
     get
    1.14
     sometimes
    1.14
     if
    1.13
    Activations Density 0.002%

    No Known Activations