© 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. 34-GEMMASCOPE-RES-131K
    7. 1120
    Prev
    Next
    INDEX
    Explanations

    html tags and descriptions

    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_34/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
     этой
    -1.20
     绿色
    -1.05
     preguntó
    -0.93
    klassen
    -0.92
    гряз
    -0.92
    IZONA
    -0.90
     сайты
    -0.89
    ведення
    -0.88
    Таблица
    -0.88
    BERRY
    -0.87
    POSITIVE LOGITS
     while
    1.53
     way
    1.16
     it
    1.09
     which
    1.03
    while
    1.01
     situations
    1.01
     whereas
    0.99
     so
    0.94
     although
    0.94
     something
    0.94
    Activations Density 0.001%

    No Known Activations