© 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. 119776
    Prev
    Next
    INDEX
    Explanations

    temozolomide and place names

    np_acts-logits-general · gemini-2.5-flash-lite

    place names, especially towns, cities, counties, and geographical locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    jaqueta
    -1.68
     surpresa
    -1.63
     și
    -1.59
     самых
    -1.54
     způ
    -1.53
    </h2>
    -1.53
    Ere
    -1.49
     solução
    -1.49
    tarta
    -1.48
    同一个
    -1.47
    POSITIVE LOGITS
     are
    1.74
    .
    1.65
    They
    1.52
    .’
    1.51
    ’
    1.48
     them
    1.48
    V
    1.47
     ними
    1.44
    atisk
    1.44
     قائمة
    1.42
    Activations Density 0.760%

    No Known Activations