© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4376
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on passages describing systemic oppression or social injustice (e.g. apartheid‐era policies and their effects).

    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
     😊
    0.86
    ☺️
    0.82
     grateful
    0.81
     versatility
    0.80
     appreciative
    0.79
    😊
    0.79
     🤗
    0.77
    拓展
    0.77
     harmonious
    0.76
     appreciation
    0.75
    POSITIVE LOGITS
     worsened
    1.59
     Worse
    1.56
     worsens
    1.51
     worse
    1.46
     worsen
    1.39
     akibat
    1.38
     worsening
    1.38
     deplorable
    1.37
     horrendous
    1.29
     peor
    1.27
    Activations Density 0.548%

    No Known Activations