© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8793
    Prev
    Next
    INDEX
    Explanations

    deception, tricks, and fake information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    s
    1.43
     EVENTS
    1.14
    B
    1.12
    ים
    1.09
    ség
    1.05
     dominion
    1.05
    ਆਂ
    1.02
    ום
    1.02
     fief
    1.00
    ന്റ്
    0.98
    POSITIVE LOGITS
     Fake
    1.38
     умолча
    1.37
    йки
    1.36
     tricks
    1.34
    騙
    1.32
    くない
    1.27
    trick
    1.27
     fake
    1.25
    詐
    1.20
    Fake
    1.20
    Activations Density 0.618%

    No Known Activations