© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14992
    Prev
    Next
    INDEX
    Explanations

    mathematical operators

    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
    Not in Any Lists

    No Comments

    Negative Logits
    вого
    -1.20
    ୩
    -1.13
    IANT
    -1.13
     lorsque
    -1.12
     ナイロン
    -1.10
    的参数
    -1.10
    asts
    -1.09
    tup
    -1.08
     rata
    -1.05
    joyed
    -1.05
    POSITIVE LOGITS
     Zeitraum
    1.23
     erfolgreichen
    1.20
     what
    1.12
     vollen
    1.10
     sincero
    1.10
     their
    1.05
     mußte
    1.04
     Mitteln
    1.03
     einzigen
    1.02
     gemeinsamen
    1.02
    Activations Density 0.050%

    No Known Activations