© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129984
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (stand-alone numbers, decimals, or other digit sequences).

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

    names after punctuation

    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
     with
    -1.29
     while
    -1.27
     ministra
    -1.25
     section
    -1.22
     during
    -1.22
     without
    -1.20
     TAMBÉM
    -1.19
     years
    -1.17
     instituto
    -1.15
     its
    -1.14
    POSITIVE LOGITS
    mmation
    1.68
    atique
    1.62
    いろんな
    1.37
    pherds
    1.32
    ığım
    1.30
    voer
    1.28
     которы
    1.27
     ayudas
    1.25
    fting
    1.25
     limpar
    1.24
    Activations Density 0.014%

    No Known Activations