© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11169
    Prev
    Next
    INDEX
    Explanations

    tokenization / attack / romantic

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

    The neuron strongly activates on the word “category” in structured product or listing descriptions.

    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
    and
    0.89
    鳩
    0.76
    CSS
    0.75
    this
    0.73
    砌
    0.73
    September
    0.71
    F
    0.71
    likes
    0.69
     hề
    0.69
    ﻦ
    0.68
    POSITIVE LOGITS
    ないと
    0.85
    ،
    0.80
     різних
    0.77
     casc
    0.75
     functionalities
    0.75
     із
    0.74
    мун
    0.74
     xgb
    0.73
    ない
    0.73
    cendo
    0.73
    Activations Density 0.001%

    No Known Activations