© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30467
    Prev
    Next
    INDEX
    Explanations

    adultery, infidelity, cheating, affair

    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_all/layer_41_width_262k_l0_big
    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
     requiring
    0.44
    PLE
    0.43
    AutoScale
    0.43
    瀑
    0.39
     sluggish
    0.39
     விய
    0.38
     workable
    0.38
     deceler
    0.38
    增速
    0.38
    稚
    0.38
    POSITIVE LOGITS
     adultery
    1.50
     adulter
    1.42
     infidelity
    1.41
     cheating
    1.12
     cheated
    0.96
     affair
    0.95
     cheat
    0.95
     fidelity
    0.89
     illicit
    0.84
     cheats
    0.83
    Activations Density 0.003%

    No Known Activations