© 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. 10-GEMMASCOPE-RES-131K
    7. 61121
    Prev
    Next
    INDEX
    Explanations

    locations and airports

    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_10/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
     pngtree
    -1.51
    »?
    -1.50
     باسلام
    -1.36
    aimeJ
    -1.34
     slechts
    -1.34
    mű
    -1.30
     lâng
    -1.30
     multiuso
    -1.30
     psychologie
    -1.29
    GUY
    -1.28
    POSITIVE LOGITS
     On
    1.68
     on
    1.51
     .....
    1.45
    .....
    1.35
     what
    1.35
     O
    1.35
     b
    1.35
     ....
    1.34
    ecznie
    1.33
     $
    1.31
    Activations Density 0.525%

    No Known Activations