© 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. 34-GEMMASCOPE-RES-131K
    7. 55995
    Prev
    Next
    INDEX
    Explanations

    licenses and console.log

    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_34/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
    🏓
    -0.69
    创建
    -0.68
     Among
    -0.65
    숍
    -0.64
     Marrow
    -0.64
     officiels
    -0.63
     auction
    -0.63
    LIS
    -0.62
     capacidad
    -0.62
     officially
    -0.62
    POSITIVE LOGITS
    ственность
    0.75
    mX
    0.71
     Zn
    0.69
    Zr
    0.69
     Tut
    0.69
     Km
    0.68
     Kosher
    0.66
     Zr
    0.65
     Burs
    0.65
    nologia
    0.63
    Activations Density 0.083%

    No Known Activations