© 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. 12553
    Prev
    Next
    INDEX
    Explanations

    examples and illustrations

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

    This neuron fires on marketing-style imperative phrases that tell the reader to “take it along with you” (or “bring it along”) when shopping or searching for related items.

    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
    itab
    0.56
    spruch
    0.53
    /");
    0.53
    ഗു
    0.53
    
    0.52
    TAB
    0.52
    ▽
    0.52
    Tabs
    0.51
    spre
    0.50
     tabPanel
    0.50
    POSITIVE LOGITS
    欲しい
    0.55
    łam
    0.54
    న్
    0.52
     convert
    0.51
     APC
    0.51
    häuse
    0.51
    ﻦ
    0.51
    нен
    0.50
     člove
    0.50
     Brahma
    0.50
    Activations Density 0.000%

    No Known Activations