© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1872
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to content words that name objects, times, or measurements—i.e. noun tokens (including proper nouns, dates, unit‐referencing terms, 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
    <unused65>
    0.73
     solcher
    0.70
     Azad
    0.66
    VERNMENT
    0.66
     Podczas
    0.63
     ChromeDriver
    0.63
     이러한
    0.62
    RestorePolicy
    0.62
     realizar
    0.62
     سایر
    0.61
    POSITIVE LOGITS
     on
    0.77
     which
    0.73
     there
    0.73
    which
    0.71
    啊
    0.71
    on
    0.71
     for
    0.71
    there
    0.70
    er
    0.69
    for
    0.68
    Activations Density 0.070%

    No Known Activations