© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    mostly + descriptor

    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
     zarówno
    -1.34
    astră
    -1.27
     slightest
    -1.24
     régiment
    -1.23
    踯
    -1.22
    蓐
    -1.21
    рант
    -1.21
     praticamente
    -1.20
    ;++
    -1.20
    orative
    -1.19
    POSITIVE LOGITS
     used
    1.37
     but
    1.30
     just
    1.30
     what
    1.28
     consisting
    1.27
     concentrated
    1.25
    But
    1.23
     if
    1.20
     these
    1.20
     consists
    1.20
    Activations Density 0.051%

    No Known Activations