© 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. 29924
    Prev
    Next
    INDEX
    Explanations

    effective altruism and impact

    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
    Negative Logits
    НК
    -0.87
     Spirito
    -0.85
    Ronaldo
    -0.84
    BRE
    -0.83
    Dictionary
    -0.82
    dende
    -0.80
    recyclerView
    -0.78
    ➤
    -0.78
    Pel
    -0.77
     Thesaurus
    -0.77
    POSITIVE LOGITS
     Effective
    1.00
     effective
    0.93
     efficacement
    0.92
     charity
    0.90
    trac
    0.90
     charitable
    0.89
     EA
    0.85
    charity
    0.85
    blusa
    0.83
     Give
    0.83
    Activations Density 0.040%

    No Known Activations