© 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. 26475
    Prev
    Next
    INDEX
    Explanations

    people and pronouns

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

    The neuron is primarily detecting object‐case personal pronouns (me, you, him, her, them).

    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
     samodziel
    -1.06
    klju
    -1.05
     neben
    -1.00
     kesk
    -0.97
     someone
    -0.97
     clairement
    -0.96
    INGER
    -0.94
     spoluprá
    -0.94
     manguera
    -0.92
    udière
    -0.92
    POSITIVE LOGITS
     in
    1.24
     on
    1.04
    ȩ
    0.88
    möglichen
    0.87
    하는
    0.87
    น
    0.86
    Làm
    0.83
     ப
    0.81
    Теперь
    0.81
    hängt
    0.80
    Activations Density 0.048%

    No Known Activations