© 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. 34-GEMMASCOPE-RES-131K
    7. 102559
    Prev
    Next
    INDEX
    Explanations

    css code snippets

    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_34/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
     that
    -1.14
    olución
    -1.04
    用に
    -1.02
     trenger
    -1.02
    PLICATIONS
    -1.02
     étrangère
    -1.00
     AppModule
    -0.98
    Não
    -0.97
    合衆
    -0.94
    nemies
    -0.94
    POSITIVE LOGITS
    /*
    1.27
    @
    1.20
    .
    1.20
    なので
    1.10
     rather
    0.98
    があり
    0.94
    總結
    0.94
    figure
    0.93
     ferait
    0.92
     Hinsicht
    0.92
    Activations Density 0.008%

    No Known Activations