© 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. 23970
    Prev
    Next
    INDEX
    Explanations

    schooling, fumes, probe, plummeting

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

    The neuron fires on words ending with the suffix “-ing.”

    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
    A
    -4.22
    The
    -3.28
    b
    -2.95
    Давайте
    -2.47
    To
    -2.47
    そういえば
    -2.39
    d
    -2.39
    Даже
    -2.38
    なんだか
    -2.36
    F
    -2.36
    POSITIVE LOGITS
     But
    3.23
    ewear
    2.63
     of
    2.58
     He
    2.50
     แต่
    2.48
    沕
    2.36
    mohon
    2.30
    潆
    2.30
    这事
    2.27
    即便是
    2.20
    Activations Density 0.007%

    No Known Activations