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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93339
    Prev
    Next
    INDEX
    Explanations

    states or conditions

    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
     manag
    -1.08
     zowel
    -1.00
    EROS
    -0.99
     الأخيرة
    -0.98
    romeda
    -0.97
     لأنه
    -0.95
     sunflowers
    -0.95
    rvore
    -0.95
     leop
    -0.93
     Harare
    -0.92
    POSITIVE LOGITS
     laſt
    1.25
     first
    1.18
     ways
    1.10
     serta
    1.09
     will
    1.09
     positions
    1.05
    üstü
    1.04
     sowie
    1.03
    joda
    1.03
     Synag
    1.02
    Activations Density 0.089%

    No Known Activations