© 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. 94024
    Prev
    Next
    INDEX
    Explanations

    official groups and surveys

    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
    あっという
    -1.30
    割と
    -1.29
    マジで
    -1.29
    ほんとに
    -1.27
    凄く
    -1.26
    なかな
    -1.25
    かなりの
    -1.22
     menik
    -1.22
     tomba
    -1.21
     hırka
    -1.21
    POSITIVE LOGITS
     task
    1.09
    "
    1.05
     ("
    1.05
    L
    1.05
    ........
    1.02
     "
    1.02
     conference
    1.02
    p
    1.02
    n
    1.02
    k
    1.01
    Activations Density 0.145%

    No Known Activations