© 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. 1540
    Prev
    Next
    INDEX
    Explanations

    safety standards and regulations

    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
     Halter
    -0.82
    它们的
    -0.81
     Atti
    -0.75
     Vittoria
    -0.74
     suburb
    -0.74
    umid
    -0.74
     sehingga
    -0.73
     Tug
    -0.70
    Informações
    -0.69
    ItemName
    -0.69
    POSITIVE LOGITS
     IEC
    1.15
    IEC
    1.13
     safety
    1.13
    safety
    0.97
     Safety
    0.87
     SAFETY
    0.86
    Safety
    0.85
     hazardous
    0.84
     Marx
    0.83
     risk
    0.79
    Activations Density 0.022%

    No Known Activations