© 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. 14045
    Prev
    Next
    INDEX
    Explanations

    calling someone ignorant

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

    The neuron fires on words naming political or ideological groups or affiliations (e.g. “Leftists,” “anti-gun Democrats,” “socialist,” “progressive”).

    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
    Télé
    0.66
    extensive
    0.63
    гро
    0.63
    kilomet
    0.63
    一开始
    0.62
    ⏭
    0.59
     extensive
    0.59
    別の
    0.59
     بداية
    0.59
    訖
    0.58
    POSITIVE LOGITS
     idiots
    0.89
     ignor
    0.74
     idiot
    0.73
     scum
    0.73
     clueless
    0.72
     incompet
    0.71
     Fauci
    0.71
    裔
    0.71
     loser
    0.69
     incompetent
    0.68
    Activations Density 0.074%

    No Known Activations