© 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. 35256
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

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

    The neuron is picking out numeric tokens (numbers or digit sequences) in the text.

    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
     навіть
    -1.03
     даже
    -0.88
     where
    -0.88
     exigen
    -0.88
     by
    -0.88
    idences
    -0.87
     brevis
    -0.87
    —
    -0.84
     berea
    -0.83
    DRA
    -0.83
    POSITIVE LOGITS
     struktur
    1.26
    teknik
    1.24
     celé
    1.07
    ㄕ
    1.02
     elegante
    1.02
     beker
    1.02
     くれ
    1.01
    espresso
    1.01
     above
    1.00
     decidi
    0.98
    Activations Density 0.001%

    No Known Activations