© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6731
    Prev
    Next
    INDEX
    Explanations

    code and licenses

    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
     delegation
    -1.00
    TTTT
    -0.81
    哲
    -0.79
     outsourced
    -0.78
     Delegation
    -0.76
    Delegate
    -0.74
     outsource
    -0.73
     delimiter
    -0.71
    空中
    -0.70
    combe
    -0.68
    POSITIVE LOGITS
     Vanguard
    1.31
    Vanguard
    1.18
     vanguard
    0.83
     Workbook
    0.76
     sentenza
    0.75
     фур
    0.74
     varies
    0.74
    йом
    0.72
     theore
    0.72
    Mean
    0.71
    Activations Density 0.006%

    No Known Activations