© 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. 129423
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (digits) in the text.

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

    Belize City

    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
    ların
    -1.23
    worfen
    -1.13
    RESUMEN
    -1.12
    🚇
    -1.12
    背影
    -1.11
    といって
    -1.11
     että
    -1.09
    に入れ
    -1.09
    ruhe
    -1.08
    leyici
    -1.07
    POSITIVE LOGITS
    "/",
    1.23
     sorgfäl
    1.18
     Belize
    1.16
     referirse
    1.14
    чал
    1.11
     bestens
    1.10
    盞
    1.09
     folhe
    1.08
    щению
    1.08
     Fähig
    1.06
    Activations Density 0.005%

    No Known Activations