© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128591
    Prev
    Next
    INDEX
    Explanations

    subjects following "the"

    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
     by
    -1.00
    Před
    -0.95
    ركة
    -0.94
     using
    -0.94
     utford
    -0.93
     Using
    -0.91
    〇〇
    -0.91
    ándole
    -0.91
    ță
    -0.90
     zult
    -0.90
    POSITIVE LOGITS
    再次
    1.12
    ↵
    1.05
     tych
    1.02
    场比赛
    1.02
     usual
    1.02
     milhões
    1.02
    connecting
    0.99
     erweiterten
    0.96
    laten
    0.95
    >
    0.94
    Activations Density 0.231%

    No Known Activations