© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14272
    Prev
    Next
    INDEX
    Explanations

    suspicious behavior detected

    np_acts-logits-general · gemini-2.5-flash-lite

    suspicious threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鯽
    0.54
    銥
    0.50
    頔
    0.49
    騁
    0.46
    蟶
    0.46
    స్తారు
    0.46
    鯢
    0.45
    劊
    0.44
    बोल
    0.44
    頎
    0.44
    POSITIVE LOGITS
     residue
    0.48
     removed
    0.44
     abruptly
    0.44
     supplied
    0.44
     left
    0.44
    ×
    0.43
     reported
    0.43
     immediately
    0.43
     clouded
    0.42
     protect
    0.42
    Activations Density 0.023%

    No Known Activations