© 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. 103990
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or ranges

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

    The neuron fires strongly on the character sequence “hat,” i.e. it detects the trigram hat wherever it appears.

    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
    (
    -3.17
    If
    -3.06
    ８
    -3.03
    In
    -2.88
    I
    -2.83
    For
    -2.72
    “
    -2.66
    When
    -2.61
    On
    -2.59
    To
    -2.55
    POSITIVE LOGITS
    ing
    3.11
    
    2.86
    鵙
    2.81
     dát
    2.78
    卝
    2.73
    ﯼ
    2.67
    荩
    2.67
    雱
    2.66
    を始め
    2.63
    értelmű
    2.56
    Activations Density 0.002%

    No Known Activations