© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112955
    Prev
    Next
    INDEX
    Explanations

    motor vehicle

    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
     europeos
    -2.16
     estadounidenses
    -1.98
    哟
    -1.97
     semblait
    -1.95
     they
    -1.95
    儅
    -1.95
    ஂ
    -1.92
     mert
    -1.88
    s
    -1.88
     prevailing
    -1.84
    POSITIVE LOGITS
    meteries
    2.66
    辚
    2.30
    -
    2.23
     kurzem
    2.19
    ೢ
    2.16
    鹪
    2.16
     tornar
    2.13
     erheb
    2.09
    磲
    2.09
    骉
    2.08
    Activations Density 0.020%

    No Known Activations