© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31619
    Prev
    Next
    INDEX
    Explanations

    poisoned, tainted, or contaminated

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

    descriptions of contamination, sabotage, or poisoning of objects or substances.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ртуаль
    -0.85
     armoured
    -0.78
    celand
    -0.77
     Idol
    -0.77
    mentar
    -0.75
     Protective
    -0.75
     phag
    -0.75
    ILIA
    -0.75
    Nuorodos
    -0.72
     unsustainable
    -0.71
    POSITIVE LOGITS
     poisoned
    1.97
     laced
    1.81
     dru
    1.77
     spiked
    1.74
     lacing
    1.52
     poisoning
    1.49
     poison
    1.49
    poison
    1.47
     contaminated
    1.41
    laced
    1.37
    Activations Density 0.030%

    No Known Activations