© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 534
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on the single, high-salience content word (typically a key noun) that appears at the start or end of a paragraph/segment, essentially picking out the “topic” or summary word of each block.

    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
    '=>'','
    0.39
     двух
    0.39
     দুই
    0.36
    ዳል
    0.36
    താണ്
    0.36
    дем
    0.36
     অধীনে
    0.35
     গিয়েছিল
    0.35
    ましたが
    0.35
    ethylsulfanyl
    0.35
    POSITIVE LOGITS
    .”
    0.76
    。
    0.75
    ."
    0.71
    .
    0.70
    。”
    0.67
    ។
    0.67
    .<
    0.65
    !
    0.64
    .\"
    0.64
    ™.
    0.64
    Activations Density 0.000%

    No Known Activations