© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7761
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by adverb or verb

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

    The neuron strongly activates on first‐person pronouns (e.g. “I,” “we”), marking instances where the author refers to themselves.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    1.02
     当
    0.97
    之后
    0.94
     όταν
    0.94
     когда
    0.93
     після
    0.93
    当
    0.93
    当你
    0.91
    當
    0.91
     khi
    0.89
    POSITIVE LOGITS
     inevitably
    1.28
     inevitable
    1.23
     automaticamente
    1.12
     inev
    1.08
     unavoid
    1.05
     naturally
    0.97
     mutlaka
    0.95
     unavoidable
    0.95
     automáticamente
    0.93
     necesariamente
    0.93
    Activations Density 0.668%

    No Known Activations