© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101313
    Prev
    Next
    INDEX
    Explanations

    dbl or ddl abbreviations

    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_10/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
    </sub>
    -3.05
    </th>
    -2.63
    钇
    -2.50
    祧
    -2.48
     简约
    -2.44
     decorada
    -2.38
    ";
    -2.34
     []
    -2.33
     皮肤
    -2.33
    </h1>
    -2.25
    POSITIVE LOGITS
    ?"
    2.98
     builds
    2.52
    !"
    2.52
    !!!!!!
    2.47
     após
    2.47
    \
    2.45
     &
    2.42
     
    2.36
    /'
    2.34
    0
    2.33
    Activations Density 0.002%

    No Known Activations