© 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. 33717
    Prev
    Next
    INDEX
    Explanations

    current time or status

    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
     generado
    -0.86
    收获
    -0.84
     spesso
    -0.84
    охра
    -0.81
     muñeca
    -0.81
     ismer
    -0.80
    வெ
    -0.79
    olahan
    -0.79
     egész
    -0.78
     começ
    -0.78
    POSITIVE LOGITS
     now
    1.51
     updated
    1.23
     terbaru
    1.10
     désormais
    1.00
     nunmehr
    0.98
     continue
    0.96
    tifiable
    0.96
    ormais
    0.94
     NOW
    0.94
    now
    0.93
    Activations Density 0.007%

    No Known Activations