© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129653
    Prev
    Next
    INDEX
    Explanations

    math and code symbols

    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
    のような
    -0.95
     decided
    -0.94
     eyel
    -0.91
     universally
    -0.87
    hermoso
    -0.86
    保湿
    -0.86
     wanted
    -0.82
     does
    -0.82
     combined
    -0.81
     specifically
    -0.81
    POSITIVE LOGITS
    rin
    0.98
    kään
    0.95
    DataItem
    0.93
    麒
    0.86
     だっ
    0.86
    ύπ
    0.86
     Spin
    0.85
     actriz
    0.85
    diction
    0.85
     apenas
    0.84
    Activations Density 0.002%

    No Known Activations