© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61366
    Prev
    Next
    INDEX
    Explanations

    degree of impact

    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
     it
    -2.08
     of
    -1.76
     a
    -1.73
     any
    -1.66
     by
    -1.51
    槐
    -1.49
    狴
    -1.48
    敺
    -1.46
     pemuda
    -1.44
    aneity
    -1.42
    POSITIVE LOGITS
     COMPOUNDS
    1.77
     or
    1.73
    ↵↵
    1.57
     adicionales
    1.50
     снова
    1.48
     различных
    1.45
     опять
    1.45
    几点
    1.45
     aceites
    1.45
     wszystkich
    1.44
    Activations Density 0.222%

    No Known Activations