© 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. 100571
    Prev
    Next
    INDEX
    Explanations

    my things and experiences

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

    The neuron is highly sensitive to the first-person possessive pronoun “my.”

    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
    镚
    -2.50
     montrent
    -2.25
    ,"
    -2.25
    泐
    -2.11
    要是
    -2.09
     для
    -2.09
     amounting
    -2.09
    眼下
    -2.06
    自制
    -2.05
     They
    -2.03
    POSITIVE LOGITS
    u
    3.17
    as
    2.80
    1
    2.69
    i
    2.66
    羕
    2.61
    ቭ
    2.41
     撮っ
    2.41
     bocca
    2.36
     weaken
    2.36
    en
    2.31
    Activations Density 0.119%

    No Known Activations