© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73132
    Prev
    Next
    INDEX
    Explanations

    completely + extreme state

    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
     of
    -2.14
     to
    -1.95
     pietre
    -1.57
     miliardi
    -1.54
    葙
    -1.53
    桖
    -1.48
     than
    -1.47
     be
    -1.45
     tantangan
    -1.44
     years
    -1.42
    POSITIVE LOGITS
     emphasized
    1.48
    一个是
    1.45
    三种
    1.43
    兩種
    1.42
     pensado
    1.42
    或者是
    1.41
     ingenting
    1.38
    两种
    1.38
     costuras
    1.37
     disposto
    1.37
    Activations Density 0.027%

    No Known Activations