© 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. 22-GEMMASCOPE-RES-131K
    4. 12550
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and code delimiters

    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
     first
    -1.09
     with
    -0.99
     during
    -0.98
     by
    -0.95
     while
    -0.94
     sebagian
    -0.94
     While
    -0.93
     برابوك
    -0.93
     khusus
    -0.92
     Because
    -0.92
    POSITIVE LOGITS
    Shown
    1.10
     hib
    0.97
    まさかの
    0.96
    pired
    0.95
    salms
    0.94
     Luka
    0.93
     veranstal
    0.92
    こっち
    0.92
    ibel
    0.91
    shown
    0.91
    Activations Density 0.004%

    No Known Activations