© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43315
    Prev
    Next
    INDEX
    Explanations

    warmer & greener

    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
     it
    -2.78
     if
    -2.05
     this
    -1.69
     any
    -1.67
     there
    -1.64
     one
    -1.60
    ladı
    -1.60
     świąte
    -1.59
     from
    -1.57
    {
    -1.57
    POSITIVE LOGITS
     será
    1.85
    "]();
    1.81
     özellikle
    1.73
     églises
    1.66
     =
    1.66
    "))
    1.64
     momentous
    1.64
    鹛
    1.63
    TOMS
    1.63
     –
    1.62
    Activations Density 0.002%

    No Known Activations