© 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. 22-GEMMASCOPE-RES-131K
    7. 34410
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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_22/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
     two
    -0.77
     Redaktion
    -0.74
    axios
    -0.74
    ̎
    -0.72
    шных
    -0.71
    newswire
    -0.69
     मिन
    -0.69
     상세
    -0.69
    殇
    -0.68
    pageX
    -0.67
    POSITIVE LOGITS
     number
    1.06
    Numero
    0.87
    reqs
    0.86
    number
    0.85
    NUMBER
    0.83
     Moles
    0.82
    个数
    0.82
     aantal
    0.81
     Eſ
    0.79
     numero
    0.78
    Activations Density 0.049%

    No Known Activations