© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59679
    Prev
    Next
    INDEX
    Explanations

    premises liability and negligence

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    タニ
    -0.78
    น้อง
    -0.77
    valente
    -0.75
    esty
    -0.74
    Solar
    -0.74
    breakpoints
    -0.74
     pêche
    -0.72
     Solar
    -0.72
     povez
    -0.72
    ऍ
    -0.71
    POSITIVE LOGITS
     dangerous
    1.29
     negligence
    1.12
     premises
    1.11
     invite
    1.11
     unsafe
    1.05
     dangers
    1.03
     perilous
    1.00
    dangerous
    1.00
     negligent
    1.00
     defective
    0.99
    Activations Density 0.010%

    No Known Activations