© 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. 75300
    Prev
    Next
    INDEX
    Explanations

    fix this

    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
    ↵↵
    -3.02
    嵓
    -2.25
     constitución
    -2.16
     encompassing
    -2.09
    .''
    -2.09
    ᥀
    -2.06
     vocación
    -1.98
    ,.
    -1.93
     fundación
    -1.92
    ࿚
    -1.89
    POSITIVE LOGITS
    in
    2.38
    饪
    2.33
    ?"
    2.00
    羕
    1.98
     ‘
    1.97
    銩
    1.91
    也
    1.90
    ‪.‬‬
    1.88
     लेकिन
    1.88
     heed
    1.80
    Activations Density 0.012%

    No Known Activations