© 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. 15472
    Prev
    Next
    INDEX
    Explanations

    int(number**0.5) + 1):

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

    The neuron strongly fires on first‐ and second‐person pronouns (especially “we” and “you”) in formal/legal text.

    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
    s
    0.86
    锴
    0.77
     acetylene
    0.75
    时代的
    0.75
    brows
    0.73
    shot
    0.73
    お問い合わせ
    0.72
     신고
    0.71
    shots
    0.71
     图片
    0.71
    POSITIVE LOGITS
    هُ
    0.82
    CBS
    0.78
    )=\{
    0.72
    jekte
    0.71
     kasnije
    0.71
    VT
    0.70
    riet
    0.70
    ни
    0.70
    Vid
    0.70
    ۇر
    0.69
    Activations Density 0.000%

    No Known Activations