© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    purpose, Zweck

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

    The neuron detects mentions of time intervals or durations (e.g., minutes, hours, days, weeks).

    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
     און
    0.93
     ૩
    0.91
     golongan
    0.87
     podendo
    0.82
     استعمال
    0.79
     ກ
    0.75
     אין
    0.75
     illetve
    0.73
     adduced
    0.73
     בע
    0.72
    POSITIVE LOGITS
    ​​
    0.82
    以前
    0.73
     ​​
    0.72
    数十
    0.69
    ￳
    0.69
    数百
    0.68
     সর্বদা
    0.68
    仍然
    0.68
    看起来
    0.66
    と考えて
    0.66
    Activations Density 0.015%

    No Known Activations