© 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. 60608
    Prev
    Next
    INDEX
    Explanations

    regular expressions and names

    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
     thousand
    -0.84
     maaaring
    -0.83
    ToMany
    -0.82
    terly
    -0.81
    TRAS
    -0.81
     normes
    -0.80
    
    -0.79
     possible
    -0.77
     élimin
    -0.76
     bestia
    -0.75
    POSITIVE LOGITS
     đâu
    0.90
     employed
    0.78
     նաև
    0.77
     Employed
    0.77
    螨
    0.74
    ACIN
    0.73
     underlined
    0.73
    .{
    0.72
     regul
    0.71
    性が
    0.71
    Activations Density 0.012%

    No Known Activations