© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103374
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite

    closing HTML or XML tags, particularly closing angle brackets in markup code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    1
    -2.56
    4
    -2.55
    2
    -2.48
    8
    -2.47
    3
    -2.33
    7
    -2.25
    6
    -2.13
    5
    -2.08
    9
    -2.06
     ensuing
    -1.88
    POSITIVE LOGITS
     conocidas
    1.96
    跸
    1.93
    +{
    1.81
     konkrét
    1.80
    木坂
    1.80
     mencionados
    1.78
     llamados
    1.78
     necesitar
    1.77
    ፨
    1.73
     famosas
    1.68
    Activations Density 0.011%

    No Known Activations