© 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. 11846
    Prev
    Next
    INDEX
    Explanations

    why don't scientists trust atoms

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

    The neuron is activated by formal, institutional or technical terms typical of official programmes, policy initiatives, commissions, and data‐oriented business contexts.

    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
     LGBTQ
    1.46
     impactful
    1.46
     reimag
    1.45
     PFAS
    1.45
     🥰
    1.38
     kiddos
    1.35
     CRISPR
    1.32
    🥹
    1.32
     TikTok
    1.30
    🩸
    1.28
    POSITIVE LOGITS
    
    1.23
    －
    0.93
     अा
    0.85
    牞
    0.85
     retarded
    0.82
    －－
    0.80
     உள்ப
    0.79
     �
    0.78
     ওই
    0.78
     mempunyai
    0.78
    Activations Density 0.067%

    No Known Activations