© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 148362
    Prev
    Next
    INDEX
    Explanations

    business and organization

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

    malicious purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    铃
    0.45
     discontinued
    0.43
    )}')
    0.43
     لكن
    0.43
     січня
    0.42
     Agosto
    0.41
    ns
    0.41
    年份
    0.40
     G
    0.40
    го
    0.39
    POSITIVE LOGITS
     หา
    0.54
     आम
    0.52
     विश्वसनीय
    0.51
     myfile
    0.50
    둴
    0.49
     दुष्प्रभावों
    0.48
     बाथरूम
    0.48
     मारपीट
    0.48
     karate
    0.47
    飲食
    0.47
    Activations Density 0.000%

    No Known Activations