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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3388
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     wickedness
    0.73
     deceived
    0.62
     wicked
    0.60
     defying
    0.59
     implique
    0.59
     wrongful
    0.57
    卧
    0.57
     impossible
    0.56
     deception
    0.55
     disobey
    0.55
    POSITIVE LOGITS
     awkwardly
    1.29
     awkward
    1.23
     cringe
    1.08
     overly
    1.02
    尷
    0.98
     bland
    0.95
     cheesy
    0.90
     jarring
    0.88
     lackluster
    0.88
     underwhelming
    0.86
    Activations Density 0.660%

    No Known Activations