© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12637
    Prev
    Next
    INDEX
    Explanations

    trust

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

    the word “trust” (and its close form “trusted”) occurring in the text.

    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
    🍭
    0.59
    ινό
    0.57
    غراف
    0.56
    കളെ
    0.55
     প্রতিদ্বন্দ্ব
    0.55
    कीस
    0.55
     concat
    0.55
    配件
    0.54
     getActivity
    0.54
    蛳
    0.54
    POSITIVE LOGITS
     trust
    3.95
    Trust
    3.70
     Trust
    3.67
     TRUST
    3.63
    trust
    3.58
    信任
    3.50
    TRUST
    3.38
     trusts
    3.36
     trusting
    3.33
     trusted
    3.23
    Activations Density 0.406%

    No Known Activations