© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    client or customer

    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
     unravel
    -1.05
    3
    -1.04
    1
    -1.03
    殍
    -1.00
     renowned
    -0.98
     zusätzlich
    -0.98
     conforming
    -0.96
     documenting
    -0.95
     spearheaded
    -0.94
     accomplishing
    -0.93
    POSITIVE LOGITS
     who
    1.51
     whom
    1.47
    whom
    1.38
     clientes
    1.16
    customers
    1.16
    bių
    1.12
    businesses
    1.11
    hips
    1.09
    𐐪
    1.09
    뭔
    1.08
    Activations Density 0.026%

    No Known Activations