© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14785
    Prev
    Next
    INDEX
    Explanations

    from my perspective

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

    The neuron is strongly activated by the self-referential pronoun “me” (especially in “to me” constructions), marking personal-opinion statements.

    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_24_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
    我们将
    0.86
     आपण
    0.75
    各大
    0.74
    我們可以
    0.71
     you
    0.69
    我们可以
    0.68
    உங்கள்
    0.68
    我们会
    0.66
     podemos
    0.65
    我們要
    0.65
    POSITIVE LOGITS
    ời
    0.77
     injunctive
    0.74
     indication
    0.71
    这意味着
    0.71
     einfacher
    0.67
    意味着
    0.64
    ében
    0.64
     signification
    0.63
     відста
    0.63
    是一种
    0.62
    Activations Density 0.080%

    No Known Activations