© 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. 130757
    Prev
    Next
    INDEX
    Explanations

    code control flow statements

    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
    -1.29
     Souver
    -1.13
     findet
    -1.07
     добраться
    -1.01
    бири
    -1.01
     подобрать
    -0.97
    cinogenicity
    -0.94
    并
    -0.94
    Več
    -0.93
    üs
    -0.92
    POSITIVE LOGITS
    !
    1.21
     ず
    1.07
     verletzt
    1.00
    イント
    0.95
    ználat
    0.94
    More
    0.93
    gruppe
    0.90
    It
    0.90
    anhão
    0.90
    excellents
    0.89
    Activations Density 0.000%

    No Known Activations