© 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. 9468
    Prev
    Next
    INDEX
    Explanations

    expressed belief

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

    The neuron strongly activates on occurrences of the word “opinion” (especially its plural “opinions”).

    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
    MESSAGE
    0.59
    }_
    0.57
    说明
    0.57
    жко
    0.57
    猟
    0.57
    Ặ
    0.55
    녘
    0.54
     cex
    0.52
    dR
    0.52
    }}$,
    0.51
    POSITIVE LOGITS
     opinions
    0.98
     পোষণ
    0.93
     opinion
    0.91
     attitudes
    0.91
     prejudices
    0.91
    看法
    0.90
     expressed
    0.88
     harb
    0.87
     Opinions
    0.86
     мнение
    0.82
    Activations Density 0.196%

    No Known Activations