© 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. 189
    Prev
    Next
    INDEX
    Explanations

    The neuron flags content‐bearing words (nouns, verbs, adjectives, adverbs) and ignores high-frequency function words.

    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
     a
    0.35
     an
    0.33
    -
    0.31
    _
    0.28
     eponymous
    0.27
    <0xC2>
    0.27
    /
    0.27
    <0xE2>
    0.26
     cosidd
    0.26
    0.25
    POSITIVE LOGITS
    👌
    0.49
    👍
    0.48
     👌
    0.45
    !!!!
    0.43
    !!!
    0.42
    ‼️
    0.41
     👍
    0.41
    ☺️
    0.40
    !!!!!
    0.40
    !।
    0.40
    Activations Density 16.653%

    No Known Activations