© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70596
    Prev
    Next
    INDEX
    Explanations

    counting numbers and related operations

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

    The neuron fires on numeric tokens, i.e. it detects numbers.

    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
     rundt
    -1.13
    ఎ
    -1.12
     administrativo
    -1.10
    ypso
    -1.09
     emocionante
    -1.08
    ﻷ
    -1.05
    atasaray
    -1.04
    niei
    -1.02
     limitar
    -1.02
     comunicar
    -1.01
    POSITIVE LOGITS
     because
    1.89
     that
    1.35
     which
    1.20
     therefore
    1.14
     whereas
    1.10
     for
    1.09
     потому
    1.07
    也是
    1.03
     if
    1.00
    atisfaction
    1.00
    Activations Density 0.055%

    No Known Activations