© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13888
    Prev
    Next
    INDEX
    Explanations

    names of people and artists

    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
    竟然是
    -1.23
    即便是
    -1.23
    更何况
    -1.21
    眛
    -1.20
     happened
    -1.20
     overcoming
    -1.19
     córdoba
    -1.17
     Like
    -1.16
     überg
    -1.16
    CLUSIVE
    -1.16
    POSITIVE LOGITS
     eller
    1.28
    」，
    1.26
     dAtA
    1.24
    ,”
    1.24
    หรือ
    1.23
    (...
    1.20
    MockMvc
    1.19
    gerichte
    1.18
     industrielle
    1.17
     SIMILAR
    1.16
    Activations Density 0.242%

    No Known Activations