© 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. 65646
    Prev
    Next
    INDEX
    Explanations

    up to X

    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
    .
    -1.27
     not
    -1.14
    1
    -1.12
     mostly
    -1.09
    0
    -1.07
     with
    -1.06
     less
    -1.03
     other
    -1.02
     only
    -1.01
     in
    -0.98
    POSITIVE LOGITS
     zelfs
    1.30
    🪩
    1.20
     Pueden
    1.13
     Parece
    1.11
     Главная
    1.10
     jopa
    1.09
     Existen
    1.02
     présidentielle
    1.02
     Tienen
    1.02
     asomb
    1.00
    Activations Density 0.029%

    No Known Activations