© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15323
    Prev
    Next
    INDEX
    Explanations

    conspiracy theories and myths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     Regime
    0.74
    বৃত্তি
    0.73
     concours
    0.71
     override
    0.69
    सहाय
    0.69
    🛣
    0.69
     Même
    0.69
     来自
    0.68
    পেক্ষ
    0.68
     ቁ
    0.67
    POSITIVE LOGITS
     misconceptions
    2.00
     misconception
    1.97
     myths
    1.90
     myth
    1.84
     falsely
    1.77
     misinformation
    1.74
     erroneously
    1.57
     misleading
    1.55
     Myth
    1.55
    Myth
    1.54
    Activations Density 0.519%

    No Known Activations