© 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. 257
    Prev
    Next
    INDEX
    Explanations

    is followed by descriptive words

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

    The neuron is primarily detecting forms of the copular “to be” (is/are/was/were, etc.).

    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
    นาย
    0.20
    及び
    0.19
    ();
    0.19
    StatusBar
    0.18
    0.18
     lainnya
    0.18
    ()->
    0.18
    ;++
    0.18
    ("/
    0.18
     '\
    0.17
    POSITIVE LOGITS
     ఒక
    0.25
    一種
    0.25
     ஒரு
    0.25
     unassuming
    0.24
     eine
    0.23
     foundational
    0.23
    intérêt
    0.23
     conceivable
    0.23
     one
    0.23
     كان
    0.22
    Activations Density 0.925%

    No Known Activations