© 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. 42132
    Prev
    Next
    INDEX
    Explanations

    in any

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

    The neuron fires on occurrences of the word “any.”

    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
     ツリー
    -1.57
    стреча
    -1.54
     huset
    -1.53
     detaljer
    -1.50
     ネタバレ
    -1.48
     sorta
    -1.48
     monnaie
    -1.45
     рассказывает
    -1.44
    𖣘
    -1.41
     понимаю
    -1.40
    POSITIVE LOGITS
     We
    1.93
     Are
    1.81
     They
    1.79
     From
    1.73
     Our
    1.67
    t
    1.67
     Those
    1.59
     These
    1.58
     Когда
    1.58
     That
    1.54
    Activations Density 0.016%

    No Known Activations