© 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. 22-GEMMASCOPE-RES-131K
    7. 15741
    Prev
    Next
    INDEX
    Explanations

    disclaimers and author notes

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

    This neuron fires on personal pronouns (e.g. “I,” “me,” “my,” “you”)—i.e. self-references and direct addresses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    :
    -1.15
    ACCIÓN
    -1.11
     then
    -1.11
    Then
    -1.10
     goku
    -1.08
     filmp
    -1.03
    /
    -1.02
     burch
    -1.02
     invitamos
    -1.02
     السياس
    -1.02
    POSITIVE LOGITS
     anjo
    1.34
     conseguiu
    1.14
    一定的
    1.13
     cuaderno
    1.13
     الشاشة
    1.12
     suceso
    1.11
     fufficient
    1.10
    ację
    1.08
     coração
    1.07
     velho
    1.07
    Activations Density 0.011%

    No Known Activations