© 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. 31665
    Prev
    Next
    INDEX
    Explanations

    danger and dangerous phrases

    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
    tdessen
    -1.01
    .)}
    -1.00
    ダウンロード
    -0.91
     deserto
    -0.90
     popolo
    -0.90
     粥
    -0.90
    ciach
    -0.88
     ſa
    -0.88
     felpa
    -0.87
     levier
    -0.87
    POSITIVE LOGITS
    ous
    1.56
    ously
    1.52
     zone
    1.37
     zones
    1.35
    danger
    1.19
     posed
    1.16
    EROUS
    1.09
     danger
    1.07
     Danger
    1.05
    ناک
    1.04
    Activations Density 0.018%

    No Known Activations