© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109385
    Prev
    Next
    INDEX
    Explanations

    Java API and 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
    xty
    -0.93
    Vegeta
    -0.89
    мыми
    -0.84
     tirar
    -0.78
     hubby
    -0.78
    𝓫
    -0.75
     Entra
    -0.75
     stiffer
    -0.75
     Să
    -0.74
    Pato
    -0.74
    POSITIVE LOGITS
    ogs
    0.81
    经常
    0.80
     muelle
    0.79
     Merri
    0.78
    Spring
    0.78
     اعتبار
    0.77
    Ско
    0.76
    posiciones
    0.76
     riego
    0.74
     avaliações
    0.74
    Activations Density 0.003%

    No Known Activations