© 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. 9776
    Prev
    Next
    INDEX
    Explanations

    insurance policy, Bingo Blitz

    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
    Look
    -1.04
     subjected
    -1.01
     deep
    -1.01
    他要
    -0.98
    bigr
    -0.96
     difficult
    -0.94
     different
    -0.93
    новая
    -0.92
     subject
    -0.91
    וּ
    -0.90
    POSITIVE LOGITS
     graines
    1.16
     diejenigen
    0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.91
    ningens
    0.90
     achie
    0.90
     angewendet
    0.89
     médicaments
    0.89
     決定
    0.88
    וך
    0.88
    泰国
    0.88
    Activations Density 0.001%

    No Known Activations