© 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. 13479
    Prev
    Next
    INDEX
    Explanations

    locations, certifications, and lists

    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
     either
    -1.07
     Именно
    -1.00
    accharide
    -0.93
    ??????
    -0.91
     пальто
    -0.90
    的笑容
    -0.90
     Πολ
    -0.90
    delijk
    -0.90
     πρ
    -0.90
    汚れ
    -0.89
    POSITIVE LOGITS
    </h2>
    2.16
    </h1>
    1.45
    </h4>
    1.37
    </b>
    1.34
    </strong>
    1.34
    </h3>
    1.32
    </h5>
    1.18
    '},
    
    1.06
     henvisninger
    1.05
     diferentes
    1.03
    Activations Density 0.006%

    No Known Activations