© 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. 34-GEMMASCOPE-RES-131K
    7. 59594
    Prev
    Next
    INDEX
    Explanations

    measuring/monitoring parameters

    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
    ссе
    -0.87
     genotyping
    -0.86
     PackageManager
    -0.82
     BoxFit
    -0.80
     mécanisme
    -0.80
    endroit
    -0.77
    موقع
    -0.77
    tration
    -0.76
     GenerationType
    -0.74
    ovali
    -0.73
    POSITIVE LOGITS
     parameters
    5.06
     parameter
    4.00
     Parameters
    3.91
    parameters
    3.84
    Parameters
    3.50
     PARAMETERS
    3.27
     Parameter
    3.20
    参数
    3.19
    parameter
    3.09
    Parameter
    3.08
    Activations Density 0.317%

    No Known Activations