© 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. 242
    Prev
    Next
    INDEX
    Explanations

    providers

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

    The neuron specializes in spotting number‐and‐symbol tokens typical of URLs’ query parameters and code/command‐line flags.

    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
    BOOK
    0.23
     й
    0.23
    getMaster
    0.22
     BOOK
    0.22
    IMG
    0.21
    ائح
    0.21
    వ్వు
    0.21
    autical
    0.20
    Obj
    0.20
    いろいろ
    0.20
    POSITIVE LOGITS
    <unused374>
    0.24
    <unused332>
    0.24
    <unused2199>
    0.24
    她说
    0.22
    <unused1645>
    0.22
     функції
    0.22
    <unused2108>
    0.22
    নাট
    0.21
     ठिकाणी
    0.21
     została
    0.21
    Activations Density 0.006%

    No Known Activations