© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37967
    Prev
    Next
    INDEX
    Explanations

    array initialization

    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
    fă
    -0.83
     growing
    -0.80
     найти
    -0.78
     Benjamin
    -0.77
     trabajando
    -0.76
    Separation
    -0.73
    σο
    -0.73
    pys
    -0.72
     réalise
    -0.72
    SuppressLint
    -0.71
    POSITIVE LOGITS
     sizeof
    2.02
     ARRAY
    1.61
    ARRAY
    1.49
    sizeof
    1.44
    array
    1.04
    Array
    1.03
     array
    0.97
     dimen
    0.96
     olika
    0.95
     Array
    0.94
    Activations Density 0.007%

    No Known Activations