© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9023
    Prev
    Next
    INDEX
    Explanations

    custom mugs or t-shirts

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

    The neuron fires on chunks of marketing‐style product description copy—i.e. promotional descriptive sentences.

    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
    ック
    0.59
     tur
    0.57
     cracked
    0.57
    孔
    0.57
     ガ
    0.56
    artifacts
    0.55
    راء
    0.55
     reproduce
    0.55
     shaded
    0.55
    вор
    0.54
    POSITIVE LOGITS
     たら
    0.63
     MBBS
    0.56
    🙍
    0.55
     đón
    0.54
     presenceData
    0.53
    🙎
    0.53
     সন্দে
    0.53
    newNode
    0.53
    <0xF2>
    0.52
     đậu
    0.52
    Activations Density 0.000%

    No Known Activations