© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1748
    Prev
    Next
    INDEX
    Explanations

    calm, peaceful

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
     vigorously
    0.56
     جعلی
    0.53
     aggressively
    0.49
     tachy
    0.49
    辣
    0.48
    ధిక
    0.48
     monstros
    0.47
     aggressive
    0.47
     outrageous
    0.46
    🤮
    0.46
    POSITIVE LOGITS
     quiet
    3.42
     calm
    3.05
    Quiet
    3.05
    quiet
    3.02
     Quiet
    2.98
     peaceful
    2.94
     tranquil
    2.89
     спокой
    2.88
     calmness
    2.83
     tranquility
    2.78
    Activations Density 0.706%

    No Known Activations