© 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. 64937
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and derivatives

    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
     flink
    -1.18
    튿
    -1.06
    アプリケーション
    -1.04
    laubt
    -1.03
     écouter
    -0.98
    ież
    -0.96
     lage
    -0.96
    ixante
    -0.95
     Inſ
    -0.94
     vitale
    -0.94
    POSITIVE LOGITS
     it
    1.04
     nine
    1.02
     four
    1.02
     seven
    1.01
     three
    0.99
     two
    0.95
     eleven
    0.95
     државе
    0.94
     one
    0.94
     find
    0.93
    Activations Density 0.012%

    No Known Activations