© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34490
    Prev
    Next
    INDEX
    Explanations

    Assistant Chief

    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
    註
    -0.79
    }{||
    -0.79
     حمام
    -0.78
     commanders
    -0.76
     commander
    -0.75
     首页
    -0.73
    又是
    -0.71
    hif
    -0.71
     şir
    -0.71
    diol
    -0.70
    POSITIVE LOGITS
     Plans
    1.38
     plans
    1.23
    plans
    1.17
     planning
    1.09
    Plans
    1.09
     staff
    0.97
     Planning
    0.94
     PLANS
    0.88
     Staff
    0.85
    asjonen
    0.84
    Activations Density 0.024%

    No Known Activations