© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3108
    Prev
    Next
    INDEX
    Explanations

    conspiracy theory

    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_16_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
    ência
    0.64
    cción
    0.60
    да
    0.59
    zló
    0.59
    놁
    0.59
    澼
    0.58
    encias
    0.57
    ،
    0.57
    abia
    0.55
    、
    0.55
    POSITIVE LOGITS
    t
    0.94
     conspiracy
    0.88
     conspiracies
    0.87
    w
    0.87
    b
    0.86
    in
    0.86
     conspir
    0.82
    g
    0.79
     that
    0.75
    ne
    0.75
    Activations Density 0.003%

    No Known Activations