© 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. 53853
    Prev
    Next
    INDEX
    Explanations

    configuration to perform

    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
     potrzeb
    -1.13
     wykorzyst
    -1.11
     mají
    -1.11
     bijzondere
    -1.09
     voorzien
    -1.06
     posiada
    -1.05
     verbinding
    -1.05
     uży
    -1.05
     voedsel
    -1.05
     needed
    -1.04
    POSITIVE LOGITS
     to
    3.42
    来
    2.30
    來
    2.11
    进行
    1.81
     来
    1.63
    Come
    1.38
     come
    1.38
    進行
    1.32
     进行
    1.29
    嚟
    1.24
    Activations Density 0.018%

    No Known Activations