© 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. 10-GEMMASCOPE-RES-131K
    7. 12091
    Prev
    Next
    INDEX
    Explanations

    played by actor names

    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
     リュ
    -1.41
    不但
    -1.38
    Причины
    -1.34
    ENDIAN
    -1.33
     手工
    -1.33
    ED
    -1.32
    k
    -1.31
    ]
    -1.27
     speziell
    -1.27
     veloce
    -1.27
    POSITIVE LOGITS
    indonesia
    1.32
    Servico
    1.28
    bten
    1.27
    atoren
    1.27
    ている
    1.27
     seperti
    1.27
     konden
    1.27
    oca
    1.25
    5
    1.23
    粍
    1.23
    Activations Density 0.010%

    No Known Activations