© 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. 103592
    Prev
    Next
    INDEX
    Explanations

    programming language syntax structure

    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
     despite
    -0.85
     palestra
    -0.85
     than
    -0.85
     Those
    -0.84
     yourself
    -0.82
     ulter
    -0.82
    Try
    -0.77
     интерес
    -0.76
    For
    -0.75
     higher
    -0.75
    POSITIVE LOGITS
    wants
    0.93
    Stellar
    0.92
    gatt
    0.88
     yel
    0.87
     puffer
    0.86
    AccountId
    0.84
     dàn
    0.84
    Honorary
    0.84
     alligator
    0.83
     CELEBR
    0.82
    Activations Density 0.010%

    No Known Activations