© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    high quality metrics

    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
    -
    -1.46
    ゴン
    -1.07
     gdyż
    -1.05
     razonable
    -1.05
     meest
    -1.05
    噥
    -1.03
     árvores
    -1.03
     a
    -1.02
     apropiado
    -1.02
    ()));
    -1.01
    POSITIVE LOGITS
     vicino
    1.27
     DELLE
    1.14
    Trimethyl
    1.09
    ֔
    1.09
    iyle
    1.06
     internazionale
    1.06
    ఝ
    1.05
    假的
    1.05
    甚至
    1.04
    러나
    1.03
    Activations Density 0.118%

    No Known Activations