© 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. 7260
    Prev
    Next
    INDEX
    Explanations

    begin with "A"

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

    The neuron activates on verbs used to give advice or suggestions (e.g. assume, consider, want).

    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
    1
    0.78
    )।
    0.76
     )।
    0.75
    ii
    0.71
     ciphertext
    0.70
     hereinafter
    0.70
     ।
    0.69
    ।
    0.68
    hana
    0.67
     vacate
    0.66
    POSITIVE LOGITS
     toneladas
    0.85
    ようやく
    0.84
     bimestre
    0.82
    将
    0.82
     outraged
    0.81
     esperado
    0.80
    磨
    0.80
    嗉
    0.79
    犹豫
    0.79
    额外
    0.78
    Activations Density 0.000%

    No Known Activations