© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5207
    Prev
    Next
    INDEX
    Explanations

    we can use method

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

    This neuron responds to the first-person plural pronoun “we” (and closely related first-person usage).

    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
     W
    0.81
     w
    0.72
    W
    0.72
    গুলিতে
    0.67
    T
    0.66
     kaikki
    0.64
    您可以
    0.63
     contended
    0.63
     T
    0.62
    0.62
    POSITIVE LOGITS
    aplik
    0.88
    itching
    0.82
    sistema
    0.82
    profissional
    0.75
    спомина
    0.74
     पहिले
    0.74
    hitung
    0.73
    ataka
    0.71
    orro
    0.71
    astikan
    0.71
    Activations Density 0.000%

    No Known Activations