© 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. 10-GEMMASCOPE-RES-131K
    7. 99798
    Prev
    Next
    INDEX
    Explanations

    HTTP status codes and technical descriptions

    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_10/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
     to
    -2.03
     the
    -1.94
     such
    -1.73
     a
    -1.66
     Then
    -1.53
    aujourd
    -1.46
    before
    -1.42
    想到了
    -1.41
     Which
    -1.40
     auß
    -1.40
    POSITIVE LOGITS
    VENTION
    1.80
    vidla
    1.70
    ൬
    1.55
    萣
    1.49
    كار
    1.47
    Etimología
    1.46
    ==",
    1.46
     Parlement
    1.45
    gidas
    1.45
    
    1.43
    Activations Density 0.002%

    No Known Activations