© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15095
    Prev
    Next
    INDEX
    Explanations

    words ending in `atable`

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

    The neuron fires on tokens containing the substring “atable,” i.e. words ending in “atable.”

    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
    ’
    -4.19
    o
    -2.97
    蹀
    -2.95
    ⟣
    -2.78
    s
    -2.69
    鹟
    -2.55
     イラストレーション
    -2.53
    stellen
    -2.45
     vaksin
    -2.39
    sion
    -2.38
    POSITIVE LOGITS
     universally
    3.14
     multifaceted
    3.08
     unwavering
    2.81
     immensely
    2.75
     enormously
    2.69
     overtly
    2.64
     invigor
    2.63
     unparalleled
    2.56
     soo
    2.55
     groundbreaking
    2.53
    Activations Density 0.010%

    No Known Activations