© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15623
    Prev
    Next
    INDEX
    Explanations

    concepts related to descriptions

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

    The neuron fires on mentions of merchandise product names—especially apparel items like “Shirt,” “Hoodie,” “Tank Top,” etc.—in promotional or e-commerce contexts.

    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
    ubehör
    0.54
    电阻
    0.49
     electrolysis
    0.49
     Optimizer
    0.48
    врат
    0.48
     electrolyte
    0.46
    ﻤ
    0.46
    ק
    0.46
     syringes
    0.45
     Electroly
    0.45
    POSITIVE LOGITS
     and
    0.59
    における
    0.59
    하거나
    0.59
     Gospels
    0.58
    และความ
    0.58
     oración
    0.57
     spirituality
    0.57
    에서의
    0.56
     captivity
    0.56
    នៃ
    0.55
    Activations Density 0.010%

    No Known Activations