© 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. 70618
    Prev
    Next
    INDEX
    Explanations

    sequential numbers and items

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

    The neuron strongly activates on numeric tokens (i.e. standalone number literals) in code or data.

    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
     its
    -1.13
     Romains
    -0.90
    рису
    -0.88
     while
    -0.87
    cings
    -0.85
    ناع
    -0.85
    "،
    -0.84
    Ṛ
    -0.84
     dizzy
    -0.84
    ТИ
    -0.83
    POSITIVE LOGITS
     third
    1.70
    third
    1.52
     Thirdly
    1.51
     troisième
    1.48
     третий
    1.27
     dritten
    1.23
    Third
    1.20
     terceira
    1.19
     derde
    1.19
     tercera
    1.19
    Activations Density 0.231%

    No Known Activations