© 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. 15582
    Prev
    Next
    INDEX
    Explanations

    damage, harm, injury, wounds

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

    harmful content

    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
    ’
    0.63
     সমস্যার
    0.61
    の問題
    0.59
    is
    0.57
     problème
    0.57
    の結果
    0.55
    ži
    0.55
     ရှိ
    0.55
    の特徴
    0.54
     शीर्षक
    0.54
    POSITIVE LOGITS
     damage
    1.16
     повре
    1.13
    damage
    1.13
    伤
    1.11
     wounds
    1.10
    伤害
    1.09
    损伤
    1.09
     Damage
    1.07
     daño
    1.05
    Damage
    1.02
    Activations Density 0.625%

    No Known Activations