© 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. 34-GEMMASCOPE-RES-131K
    7. 109168
    Prev
    Next
    INDEX
    Explanations

    Apache License, Version 2.0

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

    The neuron consistently activates on numeric literals (tokens consisting of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ((
    -1.09
    -(
    -0.95
     -(
    -0.90
     “(
    -0.85
    そこから
    -0.83
     Gummi
    -0.83
     "(
    -0.83
     '(
    -0.82
    —(
    -0.80
    ...(
    -0.78
    POSITIVE LOGITS
    %)$
    0.94
    avas
    0.93
     занима
    0.87
    ruptedException
    0.86
    dled
    0.83
    Hozzáférés
    0.82
     fanns
    0.81
    inku
    0.77
    umente
    0.76
     quí
    0.76
    Activations Density 0.075%

    No Known Activations