© 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. 10-GEMMASCOPE-RES-131K
    7. 29053
    Prev
    Next
    INDEX
    Explanations

    let questions or instructions

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

    The neuron activates on standalone numeric tokens (numbers or numeric scores) 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_10/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
     it
    -1.77
     qualquer
    -1.51
     companhia
    -1.37
    了不少
    -1.28
     what
    -1.27
     rangement
    -1.27
     дополнитель
    -1.25
    了自己的
    -1.25
    Flores
    -1.23
     how
    -1.22
    POSITIVE LOGITS
    At
    1.85
    Each
    1.84
    From
    1.77
    Once
    1.75
    Usually
    1.62
    These
    1.59
    They
    1.59
    Within
    1.51
    With
    1.51
    As
    1.51
    Activations Density 0.053%

    No Known Activations