© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69726
    Prev
    Next
    INDEX
    Explanations

    Volkswagen cars and models

    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
    se
    -1.69
    catraz
    -1.58
    s
    -1.55
    $
    -1.53
    dată
    -1.51
    și
    -1.48
    ⸰
    -1.45
    operative
    -1.43
    they
    -1.40
    i
    -1.38
    POSITIVE LOGITS
    ',
    1.73
    鈇
    1.58
    تهى
    1.50
     Volkswagen
    1.48
    "",
    1.44
    ",
    1.43
    ggiata
    1.41
     shoved
    1.40
    `,
    1.38
     echoes
    1.38
    Activations Density 0.014%

    No Known Activations