© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4333
    Prev
    Next
    INDEX
    Explanations

    deliberately manipulative persuasion

    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_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
     determinar
    0.48
     verificare
    0.43
     antennis
    0.43
     truly
    0.42
    顿时
    0.42
     respectivement
    0.41
    奋
    0.41
    跃
    0.41
     significative
    0.40
     riguarda
    0.40
    POSITIVE LOGITS
     propaganda
    0.77
     deliberately
    0.76
     strategically
    0.75
     persuasion
    0.68
     tactics
    0.67
     disinformation
    0.67
    巧妙
    0.67
     purposely
    0.67
     blackmail
    0.66
     deceptive
    0.64
    Activations Density 0.367%

    No Known Activations