© 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. 90148
    Prev
    Next
    INDEX
    Explanations

    msdn.microsoft.com/en-us/library/windows/desktop

    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
    lsb
    -0.69
     smoker
    -0.68
    Packing
    -0.68
    جه
    -0.68
     Glover
    -0.67
    NEGATIVE
    -0.67
     것이
    -0.66
    TASK
    -0.64
    ITU
    -0.63
    LSU
    -0.63
    POSITIVE LOGITS
    Compute
    0.66
    cioni
    0.65
    むしろ
    0.64
     Schlag
    0.64
    AFX
    0.63
    )`
    0.62
     traditionnelle
    0.62
    鯖
    0.61
    COMPUT
    0.61
    モル
    0.60
    Activations Density 0.064%

    No Known Activations