© 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. 106389
    Prev
    Next
    INDEX
    Explanations

    all it does is

    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
     hoort
    -1.45
     neemt
    -1.45
     brengt
    -1.28
     voelt
    -1.27
     speelt
    -1.21
     krijgt
    -1.19
     helicópter
    -1.13
    事も
    -1.12
    でしたね
    -1.11
     geldt
    -1.11
    POSITIVE LOGITS
     is
    4.81
     are
    3.20
    的是
    1.99
    คือ
    1.81
     was
    1.75
    は
    1.72
     adalah
    1.66
    是
    1.64
    is
    1.58
    는
    1.55
    Activations Density 0.042%

    No Known Activations