© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 28652
    Prev
    Next
    INDEX
    Explanations

    Defender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     \
    1.06
    ücht
    1.03
    í
    1.03
    ka
    0.96
    é
    0.93
     was
    0.93
    ı
    0.91
    и
    0.85
    q
    0.85
    ising
    0.84
    POSITIVE LOGITS
    ین
    1.42
    ม
    1.30
    م
    1.28
    ം
    1.25
    м
    1.23
     defenders
    1.21
    కు
    1.20
    ו
    1.18
    ம்
    1.13
    ні
    1.12
    Activations Density 0.002%

    No Known Activations