© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22449
    Prev
    Next
    INDEX
    Explanations

    exhibitions and art displays

    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
    縯
    -2.59
    檍
    -2.02
    鸲
    -1.97
     assuring
    -1.84
    莚
    -1.84
     believing
    -1.78
    an
    -1.75
    进去
    -1.75
    juste
    -1.74
     effortlessly
    -1.73
    POSITIVE LOGITS
     If
    2.42
    ጵ
    2.06
    ’，
    1.98
    想
    1.77
     What
    1.75
     splashes
    1.75
     如果
    1.73
    メリカ
    1.71
    lblNewLabel
    1.66
    然后
    1.66
    Activations Density 0.005%

    No Known Activations