© 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. 16757
    Prev
    Next
    INDEX
    Explanations

    FIFA 12

    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
     Vitamina
    -1.27
     CHLOR
    -1.13
    💢
    -1.08
    ductors
    -1.05
    🧩
    -1.04
     sako
    -1.02
     PHOSPH
    -1.02
    oys
    -1.02
     we
    -1.01
    ilige
    -1.00
    POSITIVE LOGITS
    caucasian
    1.09
    pushd
    1.09
     będą
    1.07
    subsubsection
    1.05
     específico
    1.05
    pertina
    1.02
     blaue
    1.02
     desblo
    1.02
     of
    1.01
    ritten
    1.01
    Activations Density 0.000%

    No Known Activations