© 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. 127313
    Prev
    Next
    INDEX
    Explanations

    piggy and kitty

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

    The neuron responds to occurrences of diminutive animal names ending in a double consonant plus “y,” especially “piggy” and “kitty.”

    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
    ↵
    -2.52
    龶
    -2.30
     RSITY
    -2.25
    \
    -2.16
    E
    -2.13
    ↵↵
    -2.13
    龵
    -2.13
    “
    -2.06
    la
    -2.05
    ت
    -2.00
    POSITIVE LOGITS
    轳
    2.89
     the
    2.67
    搽
    2.58
    𐬹
    2.38
    榖
    2.23
    —"
    2.20
     โดย
    2.17
     intric
    2.16
    杳
    2.14
    岀
    2.14
    Activations Density 0.005%

    No Known Activations