© 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. 22-GEMMASCOPE-RES-131K
    7. 129546
    Prev
    Next
    INDEX
    Explanations

    describing specific entities

    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_22/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
     diriger
    -1.82
     kompeti
    -1.57
    
    -1.55
     occuper
    -1.55
    nearly
    -1.55
     pakan
    -1.52
     genoux
    -1.50
    麃
    -1.48
     唯美
    -1.45
    roughly
    -1.44
    POSITIVE LOGITS
     at
    1.52
     increased
    1.46
    !!!!!
    1.45
     initiatives
    1.45
     this
    1.45
     multifaceted
    1.44
     an
    1.43
     contributes
    1.41
     taking
    1.39
     plethora
    1.38
    Activations Density 0.059%

    No Known Activations