© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52075
    Prev
    Next
    INDEX
    Explanations

    toxic and poison

    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_65k_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
    프트
    0.43
     తెర
    0.42
    队长
    0.41
     הו
    0.41
     થઇ
    0.39
    鹰
    0.38
     వై
    0.38
    ầng
    0.37
    ยน
    0.37
    成为了
    0.37
    POSITIVE LOGITS
     poison
    1.25
     poisonous
    1.18
     toxin
    1.17
     poisoning
    1.16
     poisons
    1.16
    poison
    1.14
     токси
    1.14
    毒
    1.14
     poisoned
    1.13
     toxicity
    1.09
    Activations Density 0.101%

    No Known Activations