© 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. 75293
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
     the
    -1.63
    さんも
    -1.59
     would
    -1.51
     Tugas
    -1.39
     sommige
    -1.34
     our
    -1.31
    ména
    -1.30
    tidig
    -1.30
    ֢
    -1.29
    nehå
    -1.27
    POSITIVE LOGITS
     a
    1.69
    нии
    1.47
    ：“……”
    1.39
    нього
    1.36
     :
    1.36
     и
    1.29
    ৄ
    1.29
    日々
    1.28
    ation
    1.27
    +}$
    1.27
    Activations Density 0.014%

    No Known Activations