© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 127726
    Prev
    Next
    INDEX
    Explanations

    currency codes BDT/UT

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    -3.75
     and
    -3.75
     with
    -3.64
     at
    -3.17
     as
    -3.17
     to
    -3.05
     on
    -3.00
     for
    -2.58
     that
    -2.58
     by
    -2.56
    POSITIVE LOGITS
     diriger
    2.64
     maniere
    2.56
     refroid
    2.56
     rafraî
    2.55
     délais
    2.48
     perpé
    2.42
     rafra
    2.41
     sécher
    2.36
     accompagner
    2.28
     bascul
    2.28
    Activations Density 0.110%

    No Known Activations