© 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. 47162
    Prev
    Next
    INDEX
    Explanations

    currently underway

    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
     when
    -1.47
     then
    -1.27
    後來
    -1.17
     когда
    -1.17
     later
    -1.13
     damaligen
    -1.11
     atunci
    -1.07
    当时
    -1.06
     instead
    -1.04
     vervolgens
    -1.02
    POSITIVE LOGITS
     сейчас
    1.66
     currently
    1.57
     but
    1.55
    currently
    1.46
     will
    1.42
     to
    1.30
     actuellement
    1.30
     with
    1.28
     Currently
    1.25
     actualmente
    1.15
    Activations Density 0.068%

    No Known Activations