© 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. 101917
    Prev
    Next
    INDEX
    Explanations

    probate executor representatives

    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
    氿
    -1.66
    loggen
    -1.61
    襌
    -1.56
     способствует
    -1.54
    nemer
    -1.54
    鰯
    -1.52
    饸
    -1.51
    offered
    -1.50
     vun
    -1.50
     estudi
    -1.50
    POSITIVE LOGITS
     that
    1.93
     with
    1.72
    ၟ
    1.68
     Öffentlich
    1.66
     only
    1.56
     highly
    1.55
     increased
    1.54
     lộ
    1.51
     enormously
    1.47
    1
    1.45
    Activations Density 0.020%

    No Known Activations