© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    load in electrical contexts

    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
    nesc
    -1.39
    laught
    -1.38
    llac
    -1.34
    vism
    -1.31
    футболка
    -1.29
    deln
    -1.28
    onej
    -1.25
    龊
    -1.25
    colata
    -1.25
    annels
    -1.23
    POSITIVE LOGITS
     any
    1.73
     estos
    1.46
     these
    1.45
     &
    1.42
    >
    1.39
    {
    1.28
     not
    1.24
     cualquier
    1.23
    ࿊
    1.18
    }
    1.17
    Activations Density 0.075%

    No Known Activations