© 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. 12280
    Prev
    Next
    INDEX
    Explanations

    explaining things that work

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

    The neuron strongly activates on common nouns in their plural form.

    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
     описы
    0.51
     poderá
    0.50
     může
    0.48
     обладает
    0.47
    薜
    0.47
     может
    0.46
     använder
    0.46
     sensitively
    0.45
     отвечает
    0.44
     може
    0.43
    POSITIVE LOGITS
     and
    0.53
     the
    0.49
     a
    0.46
    the
    0.45
    and
    0.43
    b
    0.43
    M
    0.43
    0.43
    W
    0.43
     N
    0.42
    Activations Density 0.001%

    No Known Activations