© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5595
    Prev
    Next
    INDEX
    Explanations

    punishment and penalty

    np_acts-logits-general · gemini-2.5-flash-lite

    financial penalties and punishments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瓏
    0.42
     kaleidos
    0.41
     albumin
    0.40
     phospholipids
    0.40
    দেখিতে
    0.40
     উদ্বোধন
    0.39
     ಉತ್
    0.38
     Dupont
    0.38
     kinematics
    0.38
    組立
    0.38
    POSITIVE LOGITS
     punishment
    3.48
     punishments
    3.47
     penalties
    3.34
     penalty
    3.22
     punish
    3.14
    罰
    3.11
     punished
    3.05
    罚
    3.00
     наказа
    2.97
     Punishment
    2.97
    Activations Density 0.269%

    No Known Activations