© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45221
    Prev
    Next
    INDEX
    Explanations

    conspiracy theories and distrust of institutions

    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_31_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
     a
    0.48
    पत्
    0.48
     modification
    0.47
     presence
    0.46
     bear
    0.45
     modifica
    0.45
     petición
    0.44
     vegetal
    0.43
     jei
    0.43
     script
    0.43
    POSITIVE LOGITS
     Америки
    0.48
    십니까
    0.42
     बिज़
    0.42
     Amérique
    0.41
    американ
    0.41
    沪
    0.41
     Recession
    0.41
     теории
    0.40
    ViewController
    0.40
     美国
    0.40
    Activations Density 0.008%

    No Known Activations