© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13090
    Prev
    Next
    INDEX
    Explanations

    JSDoc param tags

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

    The neuron is highly activated by the “@” symbol in user‐mention or handle tokens (social media mentions).

    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
    @
    0.68
     తి
    0.66
     returned
    0.65
     RETURN
    0.65
     высоким
    0.64
     DIAG
    0.63
     Removes
    0.63
     জি
    0.62
     Dia
    0.62
     Antrieb
    0.61
    POSITIVE LOGITS
    title
    0.73
    author
    0.71
    融
    0.68
    copyright
    0.67
    vite
    0.64
    кто
    0.63
    see
    0.62
    tablet
    0.62
    topic
    0.61
    iamine
    0.61
    Activations Density 0.013%

    No Known Activations