© 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. 8172
    Prev
    Next
    INDEX
    Explanations

    . ! Here

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

    The neuron is detecting the boundaries and content of article headlines or titles.

    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
     যেহেতু
    0.70
     Leute
    0.60
     всі
    0.55
     चूंकि
    0.55
    类似于
    0.54
    ష్టం
    0.54
     লম্বা
    0.53
    ጬ
    0.52
     거의
    0.52
     Stomach
    0.52
    POSITIVE LOGITS
     analyse
    0.71
     analys
    0.68
     继续访问
    0.67
    能否
    0.66
    を描
    0.64
    analyse
    0.63
    究竟
    0.63
    innov
    0.63
     এমনই
    0.62
    蜊
    0.61
    Activations Density 0.411%

    No Known Activations