© 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. 65673
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or punctuation

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

    The neuron activates on numeric expressions (standalone numbers and numeric measurements).

    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
     gigantic
    -1.27
    色々と
    -1.25
    ことも
    -1.23
     hefty
    -1.22
     freakin
    -1.20
    _
    -1.15
    こともある
    -1.14
     freaking
    -1.14
    割と
    -1.14
    ates
    -1.13
    POSITIVE LOGITS
     but
    1.18
    дут
    1.16
     ресни
    1.16
    felizmente
    1.12
     Autorisations
    1.10
    peka
    1.10
     mene
    1.09
    :%.
    1.09
     cerdas
    1.09
    lieben
    1.08
    Activations Density 0.031%

    No Known Activations