© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8080
    Prev
    Next
    INDEX
    Explanations

    safety and regulatory requirements

    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
    <unused589>
    0.88
     Luffy
    0.85
     Goku
    0.83
     inéd
    0.82
     Barça
    0.82
     brazil
    0.82
    getStudentNo
    0.81
    <unused1887>
    0.80
     extravaganza
    0.78
     latina
    0.78
    POSITIVE LOGITS
    セキュリティ
    0.90
     antimicrobial
    0.89
     antioxidant
    0.89
     Sicherheits
    0.88
     damping
    0.87
    防御
    0.84
    抗菌
    0.82
     Safety
    0.81
     Regulatory
    0.81
     antioxidants
    0.81
    Activations Density 0.210%

    No Known Activations