© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23768
    Prev
    Next
    INDEX
    Explanations

    trust and its erosion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ຜະລ
    0.42
     BatchNorm
    0.39
    olato
    0.37
    咆
    0.37
    ScriptAssemblies
    0.36
     ધ
    0.35
    挡
    0.35
    াঁ
    0.35
     ignorant
    0.35
    வான்
    0.35
    POSITIVE LOGITS
     trust
    1.67
    信任
    1.58
     credibility
    1.55
     trustworthiness
    1.52
    trust
    1.49
    Trust
    1.43
     Trust
    1.41
     дове
    1.35
     TRUST
    1.33
    信頼
    1.33
    Activations Density 0.015%

    No Known Activations