© 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-262K
    7. 20361
    Prev
    Next
    INDEX
    Explanations

    issues, risks, and violations

    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_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
    让自己
    0.50
    鍵
    0.47
    創造
    0.46
    रह
    0.45
    音楽
    0.45
    公主
    0.44
    論文
    0.42
    籟
    0.42
    電話
    0.42
    钥匙
    0.42
    POSITIVE LOGITS
     detect
    0.84
     violations
    0.79
     detected
    0.79
     Warnings
    0.79
     warnings
    0.77
    Severity
    0.77
     severity
    0.75
     detects
    0.75
     detection
    0.74
     alerts
    0.73
    Activations Density 0.139%

    No Known Activations