© 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. 22-GEMMASCOPE-RES-131K
    7. 68629
    Prev
    Next
    INDEX
    Explanations

    partial differential equations

    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_22/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
     This
    -2.31
     respectivas
    -2.09
    ☎️
    -2.09
    冂
    -2.06
    籟
    -1.98
     If
    -1.97
    𝐆
    -1.94
    籁
    -1.93
     могут
    -1.92
    ajuku
    -1.86
    POSITIVE LOGITS
    2
    2.44
    3
    2.30
     Responding
    2.09
    5
    2.05
     conjunction
    2.05
     Sixteen
    2.05
    6
    2.02
    </b>
    1.99
    そういえば
    1.98
     Placing
    1.98
    Activations Density 0.001%

    No Known Activations