© 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. 65157
    Prev
    Next
    INDEX
    Explanations

    filter number

    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
     was
    -1.80
    '
    -1.69
     don
    -1.61
     anún
    -1.53
     saw
    -1.50
    蚨
    -1.50
     did
    -1.42
     didn
    -1.41
     just
    -1.38
     lâmpada
    -1.34
    POSITIVE LOGITS
     our
    1.47
     variadas
    1.38
    푘
    1.38
    した後
    1.34
    氿
    1.34
     ($('#
    1.33
     Wanita
    1.32
    ayaquil
    1.32
    したのが
    1.32
    ès
    1.30
    Activations Density 0.002%

    No Known Activations