© 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. 12575
    Prev
    Next
    INDEX
    Explanations

    efecto invernadero

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

    The neuron flags proper names and named‐entity tokens (e.g. company or location names, especially with capitalization or non‐standard/foreign characters).

    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
    0.98
    是一名
    0.89
    是一个
    0.85
    ıs
    0.84
    moins
    0.82
    是一款
    0.81
    गमेंट
    0.80
    ation
    0.79
     případě
    0.79
    z
    0.79
    POSITIVE LOGITS
     dari
    1.32
     на
    1.29
     della
    1.26
     для
    1.23
     של
    1.19
     и
    1.18
     completamente
    1.18
     из
    1.17
     dello
    1.16
    จาก
    1.15
    Activations Density 0.273%

    No Known Activations