© 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. 75513
    Prev
    Next
    INDEX
    Explanations

    FOR A

    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
     heard
    -1.00
     loss
    -0.95
     will
    -0.94
     countless
    -0.91
     started
    -0.90
     made
    -0.88
    čne
    -0.88
    رحلة
    -0.87
     have
    -0.86
     becomes
    -0.86
    POSITIVE LOGITS
     tamanho
    1.13
     tamaño
    0.98
     WIL
    0.96
     size
    0.94
    Size
    0.93
    tamanho
    0.93
    size
    0.93
     pf
    0.91
     Größe
    0.91
     tamaños
    0.91
    Activations Density 0.001%

    No Known Activations