© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37834
    Prev
    Next
    INDEX
    Explanations

    diff context lines

    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
     concluded
    -0.70
     begun
    -0.67
    ifan
    -0.66
     авто
    -0.66
     Brah
    -0.65
    IRY
    -0.65
    CompleteListener
    -0.65
     Herb
    -0.64
     nifer
    -0.63
    limits
    -0.63
    POSITIVE LOGITS
    mü
    0.75
    utusan
    0.72
    鹸
    0.72
    ifen
    0.72
    ridden
    0.71
     goalkeeper
    0.70
     bekende
    0.70
     supérieurs
    0.69
     capacity
    0.69
    ostoma
    0.69
    Activations Density 0.079%

    No Known Activations