Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3725
    Prev
    Next
    INDEX
    Explanations

    death, threat, penalty, sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     broken
    1.02
    蓣
    0.99
    ação
    0.95
     Wren
    0.93
     बंट
    0.92
    南京
    0.91
     vomit
    0.88
     Broken
    0.87
     breakthrough
    0.87
    ́c
    0.87
    POSITIVE LOGITS
     intestate
    1.18
     penalty
    1.16
     мозга
    1.05
    せる
    1.03
    💀
    1.03
     Penalty
    1.00
    penalty
    0.98
    ☠
    0.96
     premat
    0.95
    蜱
    0.95
    Activations Density 0.085%

    No Known Activations