© 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. 104101
    Prev
    Next
    INDEX
    Explanations

    Milton Freewater, Q&A, Warheads, Orlando Limo

    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
    .
    -2.95
     
    -2.22
    ти
    -2.05
    \\
    -2.05
    찮
    -2.03
    头发
    -2.03
    AutoresizingMask
    -1.93
     Ganzen
    -1.88
     protéger
    -1.88
     probabilidad
    -1.88
    POSITIVE LOGITS
    ↵
    2.95
    瑧
    2.84
    there
    2.28
     Ռ
    2.27
     generalmente
    2.27
    塒
    2.03
     bandung
    2.03
     jogja
    2.02
     совета
    1.99
     problemi
    1.98
    Activations Density 0.002%

    No Known Activations