© 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. 47973
    Prev
    Next
    INDEX
    Explanations

    Q: or Lymphocyte

    np_acts-logits-general · gemini-2.5-flash-lite

    random characters in cryptographic keys and encoded data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     jahre
    -2.00
    nosed
    -1.70
     mineures
    -1.60
     登山
    -1.59
     biela
    -1.56
    missile
    -1.55
     zincir
    -1.54
    msford
    -1.52
     líqu
    -1.52
     jäsen
    -1.52
    POSITIVE LOGITS
    .
    1.92
    ]
    1.63
     `
    1.62
     newfound
    1.59
     Of
    1.52
     новым
    1.50
                
    1.48
    тов
    1.47
    She
    1.45
     quando
    1.44
    Activations Density 0.017%

    No Known Activations