© 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. 1401
    Prev
    Next
    INDEX
    Explanations

    time in milliseconds

    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
    賡
    -2.11
    ′,
    -2.05
    ’?
    -2.02
    噥
    -2.02
    
    -1.97
    avaient
    -1.96
    ⵔ
    -1.91
    菀
    -1.88
     lined
    -1.87
    为什么会
    -1.86
    POSITIVE LOGITS
     '
    3.39
    '
    3.22
    I
    2.56
    ’
    2.55
    3
    2.48
    (
    2.34
    2
    2.31
    1
    2.31
    -
    2.23
    ''
    1.98
    Activations Density 0.009%

    No Known Activations