© 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. 26722
    Prev
    Next
    INDEX
    Explanations

    high demand and desirability

    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
     berücksichtigen
    -0.97
    PageRoute
    -0.96
    辈子
    -0.95
    讓我
    -0.95
    bours
    -0.94
    還可以
    -0.91
    與
    -0.91
     Berufung
    -0.90
    kinin
    -0.88
     børn
    -0.88
    POSITIVE LOGITS
    ärin
    1.27
    饽
    1.20
     for
    1.10
     coveted
    1.10
     vanwege
    1.06
     status
    1.06
    áld
    1.05
     commodity
    1.02
     bege
    1.02
     sought
    1.02
    Activations Density 0.038%

    No Known Activations