© 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. 108750
    Prev
    Next
    INDEX
    Explanations

    risks and hazards

    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
    Примеча
    -0.85
     encountering
    -0.85
     EVENTS
    -0.81
     CONSEQU
    -0.81
     Breen
    -0.79
    PROTECT
    -0.78
     jeter
    -0.77
     ASSISTANT
    -0.77
     canina
    -0.75
    Edición
    -0.75
    POSITIVE LOGITS
     hazard
    2.44
     hazards
    1.96
     Hazard
    1.68
     safety
    1.66
     health
    1.56
     risk
    1.52
    Hazard
    1.46
    hazard
    1.46
     liability
    1.40
     Hazards
    1.37
    Activations Density 0.048%

    No Known Activations