© 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. 9126
    Prev
    Next
    INDEX
    Explanations

    PuTTY, Puducherry, Puji, Puetz

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

    The neuron strongly activates on the substring “Pu,” i.e. occurrences of the token “Pu” within words or names.

    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
    e
    -4.06
    y
    -4.03
    c
    -3.69
    ⼥
    -3.52
     公仔
    -3.02
    o
    -2.97
    洇
    -2.97
    ”،
    -2.97
    ’，
    -2.95
    n
    -2.94
    POSITIVE LOGITS
     —
    3.67
     "
    2.94
    \
    2.73
     he
    2.67
    "
    2.59
    *}[
    2.52
    vantaged
    2.48
     i
    2.48
     –
    2.47
     us
    2.44
    Activations Density 0.006%

    No Known Activations