© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100914
    Prev
    Next
    INDEX
    Explanations

    for pronouns and people

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

    The neuron fires strongly on personal, subjective statements—specifically on first- or third-person pronouns (e.g. she, we, our) together with their accompanying verbs.

    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
     jorge
    -1.29
     トラベル
    -1.25
     ToDo
    -1.23
     Requis
    -1.18
     Schaden
    -1.13
    gebäude
    -1.10
    Buon
    -1.09
     FANT
    -1.08
     別注
    -1.08
     pedro
    -1.07
    POSITIVE LOGITS
    jük
    1.10
     with
    1.05
     zdol
    1.03
    YOU
    1.02
     ComVisible
    1.01
     và
    1.01
    ffective
    1.01
    tahankan
    0.96
     zask
    0.96
    ış
    0.95
    Activations Density 0.041%

    No Known Activations