© 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. 34-GEMMASCOPE-RES-131K
    7. 57542
    Prev
    Next
    INDEX
    Explanations

    units of mass and density

    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
     transgress
    -0.93
     quarts
    -0.92
    ząd
    -0.91
    länge
    -0.90
     pasteur
    -0.89
     dars
    -0.87
     patern
    -0.86
    ஃ
    -0.86
     inau
    -0.84
    　　(
    -0.84
    POSITIVE LOGITS
     of
    1.87
     weight
    1.03
     avoir
    0.98
     веса
    0.90
    不是很
    0.86
    孰
    0.85
     concentrate
    0.85
    lais
    0.84
     bersih
    0.84
     lighter
    0.81
    Activations Density 0.028%

    No Known Activations