© 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. 77750
    Prev
    Next
    INDEX
    Explanations

    instructor or safety lesson

    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
    Swim
    -0.94
     cyclists
    -0.93
     affez
    -0.92
     cyclist
    -0.89
     bicycle
    -0.86
     Bicycle
    -0.84
    ־ה
    -0.84
     trovare
    -0.84
    勤
    -0.83
    OUNTS
    -0.82
    POSITIVE LOGITS
     instructor
    1.88
     instructors
    1.74
     experience
    1.63
     participants
    1.47
    instructor
    1.45
     safety
    1.42
    体验
    1.37
     adrenaline
    1.37
     инструк
    1.35
    Instructor
    1.30
    Activations Density 0.025%

    No Known Activations