© 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. 11503
    Prev
    Next
    INDEX
    Explanations

    T/ classification codes

    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
     rús
    -1.41
     excruciating
    -1.27
     pesada
    -1.21
    Característica
    -1.19
     relentlessly
    -1.18
    着她
    -1.18
     fool
    -1.16
     ограничи
    -1.14
     intensely
    -1.13
     frustrating
    -1.13
    POSITIVE LOGITS
    ",
    1.39
    */),
    1.31
    ");
    1.30
    bale
    1.28
    ,
    1.27
    :",
    1.25
    mêmes
    1.23
    --
    1.23
    ٨
    1.21
    especially
    1.19
    Activations Density 0.145%

    No Known Activations