© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    document API

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

    The neuron detects product or item names and titles in e-commerce or catalog-style listings.

    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
    だし
    0.67
    𝓷
    0.57
     siebie
    0.56
    Alone
    0.55
     Alone
    0.55
    淵
    0.55
    紘
    0.55
     Differ
    0.54
    ]-->
    0.54
    扱い
    0.53
    POSITIVE LOGITS
     with
    0.99
     featuring
    0.98
    featuring
    0.86
    with
    0.84
     WITH
    0.84
    キット
    0.82
     avec
    0.80
     עם
    0.79
     With
    0.78
     dengan
    0.78
    Activations Density 0.506%

    No Known Activations