Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8204
    Prev
    Next
    INDEX
    Explanations

    giving instructions or commands

    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
    hours
    -0.98
    perrt
    -0.98
    juje
    -0.97
    straint
    -0.87
    hrs
    -0.86
    Hours
    -0.85
    loride
    -0.83
     jour
    -0.83
     Inbox
    -0.83
    Ouverture
    -0.82
    POSITIVE LOGITS
     instructions
    1.99
     commands
    1.79
     instruction
    1.77
     instructing
    1.71
     coaching
    1.61
     verbal
    1.60
     directing
    1.60
     communication
    1.54
     verbally
    1.48
     instruct
    1.46
    Activations Density 0.024%

    No Known Activations