© 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. 39142
    Prev
    Next
    INDEX
    Explanations

    determiner or pronoun followed by noun

    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
     perpé
    -1.06
     България
    -1.03
     случаях
    -1.02
    ERÍA
    -0.98
    的一声
    -0.92
     Matter
    -0.92
     правый
    -0.91
    んですよね
    -0.91
    Senegal
    -0.91
     jego
    -0.90
    POSITIVE LOGITS
     this
    1.68
     ultimately
    1.24
     your
    1.17
    CUDA
    1.11
     may
    1.10
    你的
    1.05
    UPAC
    1.05
     also
    1.05
     Gesund
    1.05
     these
    1.05
    Activations Density 0.017%

    No Known Activations