© 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. 99906
    Prev
    Next
    INDEX
    Explanations

    words starting with "Per"

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

    The neuron strongly activates on the exact token “Per,” i.e. occurrences of the subword “Per” used as a standalone token.

    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
     they
    -3.58
    ſſel
    -3.36
    蝋
    -2.63
    ⵈ
    -2.55
    ी
    -2.47
    ⡦
    -2.44
    謇
    -2.41
    悭
    -2.38
     we
    -2.36
     deserto
    -2.33
    POSITIVE LOGITS
     They
    3.33
    How
    3.06
    What
    2.94
     mereka
    2.81
    他們
    2.75
    2
    2.75
     國際
    2.67
    There
    2.66
    1
    2.66
    Of
    2.64
    Activations Density 0.008%

    No Known Activations