© 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. 48159
    Prev
    Next
    INDEX
    Explanations

    callbacks, currencies, trademarks, workflows

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

    The neuron strongly activates on occurrences of the word “callbacks.”

    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
    er
    -4.53
    n
    -3.80
    e
    -3.64
    en
    -3.13
    an
    -3.00
    o
    -2.92
    in
    -2.88
    y
    -2.64
    ization
    -2.59
    胧
    -2.59
    POSITIVE LOGITS
     戰
    2.44
     příjem
    2.39
     oír
    2.34
    瀟
    2.27
    選ぶ
    2.25
    噥
    2.25
     arbeit
    2.23
     obsolete
    2.22
    ↵↵
    2.22
    extAlignment
    2.20
    Activations Density 0.012%

    No Known Activations