© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106236
    Prev
    Next
    INDEX
    Explanations

    become aware, less sitting, cardiac enlargement

    np_acts-logits-general · gemini-2.5-flash-lite

    content in blog posts or articles with personal reflections, especially when discussing self-improvement, psychology, or wellness topics.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
     inusual
    -1.02
     happiness
    -0.94
     comenzado
    -0.93
     konzent
    -0.93
     positiva
    -0.91
    人には
    -0.90
     enoj
    -0.88
     indios
    -0.88
    virt
    -0.88
     positive
    -0.87
    POSITIVE LOGITS
     softwares
    1.00
     stagnation
    0.98
    acao
    0.96
     cacao
    0.93
     activations
    0.93
     Fucking
    0.92
     energetically
    0.91
    PRNewswire
    0.90
     fucking
    0.88
     energe
    0.87
    Activations Density 0.015%

    No Known Activations