© 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. 10-GEMMASCOPE-RES-131K
    7. 303
    Prev
    Next
    INDEX
    Explanations

    political and government entities

    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_10/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
     there
    -1.24
    THERE
    -1.19
     misión
    -1.19
    GIUM
    -1.14
     тук
    -1.13
     œuvre
    -1.13
    ípio
    -1.13
     efek
    -1.12
    在这里
    -1.11
     ceremonia
    -1.11
    POSITIVE LOGITS
    んでる
    1.38
    belline
    1.25
     this
    1.14
     wouldn
    1.13
     ООО
    1.13
     instead
    1.10
    んでいます
    1.09
    gı
    1.09
     Stormwater
    1.05
     called
    1.05
    Activations Density 0.190%

    No Known Activations