© 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. 2593
    Prev
    Next
    INDEX
    Explanations

    each followed by a noun

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

    This neuron consistently fires on the word “Each,” especially when it appears at the start of a clause or sentence.

    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
    glichkeiten
    1.14
    normals
    1.12
     niemals
    1.11
     hingegen
    1.09
    
    1.09
    
    1.06
    けど
    1.04
    뎐
    1.03
    办法
    1.01
    𝗯
    1.01
    POSITIVE LOGITS
     einzelnen
    1.41
     respective
    1.39
     successive
    1.36
    ين
    1.19
     individually
    1.12
     Mỗi
    1.11
     해당하는
    1.10
     separately
    1.09
     каждым
    1.08
     প্রত্যেকের
    1.05
    Activations Density 0.060%

    No Known Activations