© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24433
    Prev
    Next
    INDEX
    Explanations

    toxicity and poisoning

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

    toxic or poisoning

    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_262k_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
    하는
    0.55
    avoz
    0.55
    ূর্তি
    0.54
    paging
    0.54
    нік
    0.52
    inį
    0.52
     গাড়ি
    0.51
    쩍
    0.51
     যাত্র
    0.51
    graduation
    0.50
    POSITIVE LOGITS
     toxins
    0.96
     poisons
    0.94
     Poison
    0.92
     serums
    0.88
     poisoning
    0.87
     poisonous
    0.87
     Toxic
    0.85
     toxic
    0.84
     Toxicity
    0.82
    毒
    0.82
    Activations Density 0.031%

    No Known Activations