© 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. 10-GEMMASCOPE-RES-131K
    7. 98717
    Prev
    Next
    INDEX
    Explanations

    alphabet, set, or system

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     and
    -1.98
     at
    -1.95
     this
    -1.77
     out
    -1.66
     if
    -1.55
     an
    -1.52
     For
    -1.48
     in
    -1.43
     de
    -1.40
     through
    -1.38
    POSITIVE LOGITS
     mostrarán
    1.71
     作り方
    1.49
     harán
    1.48
     -}
    1.42
     venge
    1.35
    asanjo
    1.35
    ்கள்
    1.34
     permitem
    1.33
     PUSTAKA
    1.32
    ficit
    1.31
    Activations Density 0.109%

    No Known Activations