© 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. 22-GEMMASCOPE-RES-131K
    7. 36016
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
     Leute
    -0.93
    겨
    -0.91
    estament
    -0.91
     Furcht
    -0.87
     herein
    -0.86
     this
    -0.85
     Oh
    -0.85
     Re
    -0.84
    ://
    -0.84
    district
    -0.84
    POSITIVE LOGITS
     Áng
    0.98
     Obt
    0.94
     toilette
    0.93
     Pave
    0.92
    缫
    0.92
     Valentín
    0.90
     samego
    0.90
     traverser
    0.90
    וז
    0.89
     実例
    0.89
    Activations Density 0.003%

    No Known Activations