Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7687
    Prev
    Next
    INDEX
    Explanations

    parameter

    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
     Sleepy
    -0.82
     industriel
    -0.75
    umos
    -0.75
    PyExc
    -0.74
    itele
    -0.74
    Sleep
    -0.73
    Police
    -0.72
    Medicine
    -0.71
    ती
    -0.71
    τικό
    -0.71
    POSITIVE LOGITS
     parameter
    2.05
    parameter
    1.86
    Parameter
    1.86
     Parameter
    1.77
     парамет
    1.69
     parametri
    1.50
    参数
    1.49
     PARAMETER
    1.43
     parameters
    1.43
    Param
    1.37
    Activations Density 0.047%

    No Known Activations