© 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. 56678
    Prev
    Next
    INDEX
    Explanations

    rich tycoon

    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
    ISPR
    -0.88
    mueble
    -0.82
     Pets
    -0.82
    Pets
    -0.80
    ultz
    -0.79
     voters
    -0.79
    姐姐
    -0.78
    🧦
    -0.78
    atrix
    -0.78
     cương
    -0.76
    POSITIVE LOGITS
     brothers
    1.38
    Brothers
    1.27
    兄弟
    1.23
     boss
    1.22
    brothers
    1.21
     Boss
    1.19
    Boss
    1.09
     Brothers
    1.09
    boss
    1.09
     Brother
    1.01
    Activations Density 0.001%

    No Known Activations