© 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. 129343
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically fires on the numeral “3” when it appears in a sequence of numbers.

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

    numbers, equations, and lists

    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
     necessária
    -1.58
     adequada
    -1.51
     conhecida
    -1.51
     aberta
    -1.44
     isolada
    -1.44
     semelhante
    -1.43
     diminuer
    -1.42
     parecia
    -1.38
     entrevist
    -1.37
     extremamente
    -1.35
    POSITIVE LOGITS
    !!!!
    1.22
    LARE
    1.15
    안
    1.11
     for
    1.11
    Bor
    1.10
    Теперь
    1.09
    етка
    1.06
     forKey
    1.05
    @[+][
    1.05
    !!!!!
    1.05
    Activations Density 0.000%

    No Known Activations