© 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. 99357
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by actions/prepositions

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

    The neuron detects first- and second-person pronouns (e.g. “me,” “us,” “you”).

    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
     not
    -1.28
    CHREIB
    -1.25
    ↲
    -1.23
    rénées
    -1.19
    be
    -1.13
     не
    -1.09
    READ
    -1.09
    ed
    -1.09
    disabled
    -1.08
     هستند
    -1.08
    POSITIVE LOGITS
    这些人
    1.11
     segera
    1.04
     diverso
    1.00
    を探す
    1.00
     or
    1.00
    SFC
    0.99
     какво
    0.99
     различни
    0.99
     obtenido
    0.98
     suelo
    0.96
    Activations Density 0.066%

    No Known Activations