© 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. 22-GEMMASCOPE-RES-131K
    7. 16488
    Prev
    Next
    INDEX
    Explanations

    We/I will/can/are

    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
     which
    -1.19
     instead
    -1.18
     why
    -1.03
     its
    -1.00
     other
    -0.98
     it
    -0.96
    textnormal
    -0.96
     then
    -0.93
    oggi
    -0.92
     what
    -0.91
    POSITIVE LOGITS
     även
    1.13
    tifications
    1.11
     escul
    1.09
    chenkt
    1.06
     ако
    1.04
    inely
    1.03
    cnia
    1.03
    peño
    1.02
    ől
    1.01
     semestre
    1.01
    Activations Density 0.049%

    No Known Activations