© 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. 10-GEMMASCOPE-RES-131K
    7. 11575
    Prev
    Next
    INDEX
    Explanations

    inability of or to

    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
     休閒
    -2.58
    中国
    -2.28
    ihr
    -2.23
     Ländern
    -2.17
    تیجه
    -2.16
    One
    -2.14
    羕
    -2.13
    輕鬆
    -2.11
    Koordinaten
    -2.11
    When
    -2.08
    POSITIVE LOGITS
    ↵
    2.94
    辚
    2.39
    ).
    2.36
    骉
    2.23
     autorización
    2.14
     quindi
    2.13
    尨
    2.09
     somente
    2.09
    肏
    2.06
     possono
    2.02
    Activations Density 0.001%

    No Known Activations