© 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. 22-GEMMASCOPE-RES-131K
    7. 130997
    Prev
    Next
    INDEX
    Explanations

    numbers, commas, and parentheses

    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_22/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
    OON
    -1.02
     solution
    -0.93
    oen
    -0.91
     grà
    -0.89
     τοῦ
    -0.85
    藪
    -0.85
    薮
    -0.84
    疋
    -0.84
    ви
    -0.84
    thor
    -0.84
    POSITIVE LOGITS
    Both
    0.99
    どちらも
    0.99
     BOTH
    0.90
     ambos
    0.88
    每个
    0.87
    両方
    0.87
    8
    0.86
     Beide
    0.84
    这两个
    0.84
    3
    0.83
    Activations Density 0.026%

    No Known Activations