© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    energy cultivator stages

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

    The neuron responds to the last content word immediately before a comma—that is, the final word of a clause right before “,”.

    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
    reiche
    0.94
    ﺷ
    0.92
     মজার
    0.87
     Нью
    0.86
     alcun
    0.84
    ﺻ
    0.82
     Челябин
    0.81
    全ての
    0.81
     কারণ
    0.80
     Андроид
    0.80
    POSITIVE LOGITS
    aments
    0.69
     videre
    0.66
     partitions
    0.64
     festivities
    0.63
     further
    0.63
    ı
    0.63
     indist
    0.63
     folks
    0.62
     fest
    0.61
     crayons
    0.61
    Activations Density 0.000%

    No Known Activations