© 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. 22-GEMMASCOPE-RES-131K
    7. 66567
    Prev
    Next
    INDEX
    Explanations

    foreign or local organization

    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
     sólo
    -1.15
     violento
    -1.12
    crizione
    -1.11
     eeuw
    -1.02
     multiplied
    -1.00
     surla
    -1.00
     листь
    -0.98
    chans
    -0.97
     dollars
    -0.97
     ordinary
    -0.96
    POSITIVE LOGITS
    给我们
    1.30
    このような
    1.28
    给大家
    1.27
     również
    1.22
    lapsingToolbar
    1.12
     می‌باشد
    1.09
     our
    1.09
     splendor
    1.08
    Toward
    1.07
     alltid
    1.05
    Activations Density 0.078%

    No Known Activations