© 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. 183839
    Prev
    Next
    INDEX
    Explanations

    procur, prefect, process, Pref

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

    architectural and technical terms

    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
    資
    0.50
     artículos
    0.49
     Tư
    0.49
    یم
    0.48
     Bugünkü
    0.48
    negara
    0.48
    сті
    0.47
    樎
    0.47
    鎗
    0.46
     myös
    0.46
    POSITIVE LOGITS
     procur
    0.52
     Pref
    0.50
    ↵
    0.49
     prefect
    0.49
     Procur
    0.48
     పూర్తిగా
    0.46
     elog
    0.45
     malef
    0.45
     dro
    0.44
     cie
    0.44
    Activations Density 0.000%

    No Known Activations