© 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. 8551
    Prev
    Next
    INDEX
    Explanations

    financial misconduct and corruption

    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
     =
    1.05
     only
    0.96
     euclidean
    0.95
    atience
    0.93
     time
    0.91
     Euclidean
    0.91
     Mode
    0.91
     sweeter
    0.90
     irrespective
    0.89
    ^
    0.89
    POSITIVE LOGITS
    Corruption
    1.43
     भ्रष्टाचार
    1.33
     corrupción
    1.29
    corruption
    1.28
     bribery
    1.27
    Fraud
    1.25
     prosecutors
    1.20
     scandals
    1.18
     रिश्वत
    1.16
    Prosecutors
    1.14
    Activations Density 0.224%

    No Known Activations