© 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. 34-GEMMASCOPE-RES-131K
    7. 6699
    Prev
    Next
    INDEX
    Explanations

    go beyond

    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_34/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
    Fernsehserie
    -0.83
    時間で
    -0.82
    },[])
    -0.81
     Kün
    -0.79
     سایر
    -0.78
    チャンス
    -0.77
     różnych
    -0.77
     amines
    -0.77
    Sprache
    -0.76
     ハウス
    -0.75
    POSITIVE LOGITS
     above
    2.27
     out
    2.11
    Above
    1.69
    above
    1.61
     extra
    1.55
     Above
    1.54
     beyond
    1.40
     acima
    1.38
     ABOVE
    1.36
     far
    1.35
    Activations Density 0.008%

    No Known Activations