© 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. 75271
    Prev
    Next
    INDEX
    Explanations

    numbers followed by / or -

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

    The neuron strongly activates on tokens that are purely numerical (multi-digit number strings).

    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
     a
    -2.50
    にします
    -2.30
    corrhi
    -2.23
    に行った
    -2.05
    感じで
    -2.00
    の商品
    -2.00
    の為
    -1.97
    の準備
    -1.92
    で使
    -1.91
    に必要な
    -1.87
    POSITIVE LOGITS
    n
    2.17
    は
    2.16
    m
    2.16
    を
    2.09
    s
    2.09
    もある
    2.08
    そうですが
    2.00
    2
    1.98
    <bos>
    1.95
    などが
    1.88
    Activations Density 0.082%

    No Known Activations