© 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. 128297
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeral tokens (digit sequences) – i.e. it identifies numbers (numeric literals) in the text.

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

    mathematical notation and code snippets

    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
     onResume
    -1.25
     abusi
    -1.24
     NEWTON
    -1.23
     partecipare
    -1.22
     condividere
    -1.21
    wige
    -1.18
    ченная
    -1.16
    ongen
    -1.16
     pfalz
    -1.16
    OBJETIVO
    -1.14
    POSITIVE LOGITS
    ଵ
    1.16
     оружия
    1.13
     our
    1.13
    )=>{
    1.12
     suéter
    1.09
    馮
    1.05
     fourth
    1.05
    isMethod
    1.05
     peuples
    1.04
     የ
    1.03
    Activations Density 0.010%

    No Known Activations