© 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. 54133
    Prev
    Next
    INDEX
    Explanations

    RFC and ISO standards

    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
     low
    -0.95
     enhance
    -0.94
     enhancing
    -0.94
     first
    -0.93
     eliminates
    -0.91
    主婦
    -0.90
     remove
    -0.89
     all
    -0.88
     providing
    -0.88
     establishing
    -0.88
    POSITIVE LOGITS
     certificación
    0.93
    ssch
    0.88
    recently
    0.88
     Lorsque
    0.86
    behör
    0.85
    Į
    0.85
     disgruntled
    0.85
    wände
    0.85
    inu
    0.83
     Dharma
    0.82
    Activations Density 0.013%

    No Known Activations