© 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. 84161
    Prev
    Next
    INDEX
    Explanations

    don't know or understand

    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
     locatie
    -1.01
    dė
    -1.01
    egrave
    -1.01
     constater
    -0.99
     trám
    -0.98
    ₑ
    -0.96
    ízo
    -0.96
    आई
    -0.95
     probablement
    -0.95
    只是
    -0.95
    POSITIVE LOGITS
     know
    2.91
     think
    2.05
     want
    1.73
     why
    1.60
     even
    1.60
     understand
    1.57
     usually
    1.41
     thinks
    1.37
     have
    1.37
     knows
    1.34
    Activations Density 0.027%

    No Known Activations