© 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. 40382
    Prev
    Next
    INDEX
    Explanations

    including or excluding options

    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
     ebenfalls
    -0.87
     소녀
    -0.87
     опять
    -0.85
     Тогда
    -0.85
     insi
    -0.84
     diner
    -0.82
    ことなく
    -0.80
     paradig
    -0.79
    SUGGEST
    -0.78
    ULAR
    -0.78
    POSITIVE LOGITS
     Organisateur
    1.16
     Meilleures
    1.02
     even
    1.02
     dekoratif
    1.02
     modifikasi
    0.99
     ANCHE
    0.98
     DELHI
    0.98
     pesar
    0.98
    Only
    0.97
    Even
    0.95
    Activations Density 0.094%

    No Known Activations