© 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. 39469
    Prev
    Next
    INDEX
    Explanations

    Modern Living, URLs, names

    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
     of
    -1.23
    quarelle
    -1.01
    めでとう
    -1.00
     撮影
    -0.99
    ಞ
    -0.97
     immediately
    -0.95
    ต่อไป
    -0.95
     but
    -0.95
     any
    -0.94
    liferay
    -0.93
    POSITIVE LOGITS
    neling
    1.16
    ↵↵↵↵↵↵↵↵↵↵↵
    1.16
     ❤️
    1.12
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.06
    所说
    1.05
    خخ
    1.04
     -,
    1.03
     (~(
    1.03
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.02
    Activations Density 0.005%

    No Known Activations