© 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. 38433
    Prev
    Next
    INDEX
    Explanations

    definitely or surely

    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
     möge
    -0.95
    izophren
    -0.90
     siquiera
    -0.90
     prácticamente
    -0.90
     tendrás
    -0.88
     aldri
    -0.87
     anymore
    -0.86
     erklärte
    -0.85
    chapper
    -0.84
    larla
    -0.82
    POSITIVE LOGITS
     for
    3.38
     definitely
    3.08
    definitely
    2.33
    Definitely
    2.22
     sure
    2.09
     sicuramente
    1.98
     Definitely
    1.96
     fors
    1.96
     surely
    1.93
    for
    1.91
    Activations Density 0.027%

    No Known Activations