© 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. 8778
    Prev
    Next
    INDEX
    Explanations

    end of sentence or list item

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

    The neuron flags non‐function “content” words—i.e. informative nouns, verbs, and adjectives rather than common stopwords.

    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
     অচেতন
    0.63
     जताया
    0.62
    <unused2123>
    0.61
    烪
    0.60
    <unused715>
    0.60
    <unused1032>
    0.60
     আনুশকা
    0.60
     ім
    0.59
    Демо
    0.59
    <unused91>
    0.58
    POSITIVE LOGITS
    はない
    0.55
    ok
    0.55
    af
    0.52
    art
    0.51
    alas
    0.51
     Stand
    0.50
    ait
    0.50
     Kafka
    0.50
    het
    0.49
    okk
    0.49
    Activations Density 0.846%

    No Known Activations