© 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. 34-GEMMASCOPE-RES-131K
    7. 84047
    Prev
    Next
    INDEX
    Explanations

    and followed by past tense verbs

    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_34/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
     and
    -1.23
    ieniem
    -1.15
    tiness
    -1.08
     été
    -1.05
    ków
    -0.99
     faſt
    -0.98
    aneously
    -0.98
     ۲۰
    -0.96
     /-
    -0.96
    鉏
    -0.95
    POSITIVE LOGITS
     monitored
    1.06
    escalier
    0.93
     analyzed
    0.90
     supervised
    0.90
     deren
    0.89
     sized
    0.88
     documented
    0.87
     photographed
    0.86
     interrelated
    0.85
     maintained
    0.85
    Activations Density 0.092%

    No Known Activations