© 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. 9667
    Prev
    Next
    INDEX
    Explanations

    input values

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

    The neuron fires on tokens that are numeric literals (digits or numbers, including integers and decimals).

    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
    \
    -1.82
    '
    -1.59
     podía
    -1.59
     but
    -1.52
     that
    -1.50
    岿
    -1.45
     tuviera
    -1.45
     dalamnya
    -1.43
     estuviera
    -1.41
    "
    -1.40
    POSITIVE LOGITS
    ту
    1.59
     familières
    1.58
    泐
    1.53
    ⒈
    1.51
    渕
    1.50
    ﯼ
    1.50
    меди
    1.48
     после
    1.48
     начать
    1.47
    ⩕
    1.47
    Activations Density 0.010%

    No Known Activations