© 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. 84168
    Prev
    Next
    INDEX
    Explanations

    node elements like data, item, or key

    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
    ੦
    -0.84
    覷
    -0.82
    uhnya
    -0.81
     Wartawan
    -0.81
     új
    -0.81
     mewah
    -0.80
    लाइन
    -0.80
     klaar
    -0.80
     toate
    -0.79
     Divisional
    -0.79
    POSITIVE LOGITS
     data
    1.48
     value
    1.48
     information
    1.26
     info
    1.23
     cargo
    1.19
    data
    1.13
     next
    1.10
     content
    1.09
     contents
    1.09
     val
    0.98
    Activations Density 0.025%

    No Known Activations