© 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. 12088
    Prev
    Next
    INDEX
    Explanations

    sheen, keen, scene

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

    The neuron is highly sensitive to numeric tokens and date/event–related expressions, flagging numbers, ordinals, and date ranges that describe schedules or counts.

    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
     एप्प
    0.84
     comput
    0.77
     privacy
    0.70
     binatang
    0.70
     -*-
    0.69
     risulta
    0.69
    <0x11>
    0.68
     हिन्दू
    0.68
     ⚫
    0.68
    های
    0.68
    POSITIVE LOGITS
     additionally
    0.86
    咱们
    0.83
     adenine
    0.82
    ⾯
    0.80
     ampere
    0.79
    咗
    0.78
     strolling
    0.72
    嚟
    0.71
    פּ
    0.71
    嘅
    0.70
    Activations Density 0.438%

    No Known Activations