© 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. 13552
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    <td>
    -2.05
    Gruss
    -1.88
     baumwolle
    -1.86
     vya
    -1.77
     anhänger
    -1.67
     ambayo
    -1.63
    sepatu
    -1.59
    秾
    -1.59
     (/
    -1.59
     rústico
    -1.56
    POSITIVE LOGITS
     jsou
    1.75
    翃
    1.70
    naphthal
    1.59
     crux
    1.56
    явления
    1.55
     unsure
    1.54
     भी
    1.53
    圃
    1.52
     條
    1.50
    しました
    1.49
    Activations Density 0.043%

    No Known Activations