© 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. 48003
    Prev
    Next
    INDEX
    Explanations

    Kudos and names

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

    The neuron fires on capitalized personal names (proper names of people).

    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
    訁
    -2.92
    癭
    -2.58
    ⩴
    -2.47
    盦
    -2.38
    鶿
    -2.33
    휀
    -2.19
    🧌
    -2.16
    畱
    -2.13
    dengan
    -2.09
    してます
    -2.09
    POSITIVE LOGITS
    “
    3.02
     notre
    2.55
     Our
    2.39
     $^{\
    2.38
    '
    2.34
    用
    2.33
     meander
    2.30
    are
    2.27
    ون
    2.13
     nascent
    2.13
    Activations Density 0.005%

    No Known Activations