© 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. 125
    Prev
    Next
    INDEX
    Explanations

    email domains

    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
     to
    -1.03
     kleinere
    -1.03
     technisch
    -0.99
    both
    -0.99
    and
    -0.98
     标题
    -0.92
     momentan
    -0.90
     erns
    -0.89
    currently
    -0.89
     titans
    -0.89
    POSITIVE LOGITS
    ፝
    1.09
    elerik
    1.09
    gmail
    1.08
     pulito
    1.05
    forRoot
    1.04
    。（
    1.02
    RegistryLite
    1.02
     느
    1.02
     uvas
    1.02
     ataca
    1.01
    Activations Density 0.010%

    No Known Activations