© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9632
    Prev
    Next
    INDEX
    Explanations

    overnight attack

    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_31_width_16k_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
    ILABLE
    0.50
    ymethyl
    0.43
     ಅವಕಾಶ
    0.42
    lossen
    0.42
    যার
    0.41
    ைகளை
    0.40
     withd
    0.40
    ｭ
    0.39
    ATION
    0.39
    NING
    0.39
    POSITIVE LOGITS
     …
    0.54
     _____
    0.52
     How
    0.50
     أيضًا
    0.49
     What
    0.48
     ().
    0.48
    <0xC2>
    0.47
     TikTok
    0.47
     About
    0.46
     […]
    0.45
    Activations Density 0.035%

    No Known Activations