© 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. 31-GEMMASCOPE-2-RES-16K
    7. 442
    Prev
    Next
    INDEX
    Explanations

    The neuron generally lights up on substantive content words (key nouns, verbs, and adjectives) rather than on function words or punctuation.

    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_31_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
    D
    0.27
    V
    0.27
    X
    0.26
    H
    0.25
    F
    0.25
    S
    0.23
    E
    0.22
    A
    0.22
    N
    0.22
    K
    0.21
    POSITIVE LOGITS
     ristorante
    0.27
     ….
    0.27
    <unused581>
    0.27
     grime
    0.26
    deserved
    0.26
     unapolog
    0.26
     शानदार
    0.26
    <unused2037>
    0.26
    <unused1057>
    0.25
    <unused2199>
    0.25
    Activations Density 4.131%

    No Known Activations