© 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. 87180
    Prev
    Next
    INDEX
    Explanations

    when the

    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
    −/−
    -1.57
    inerario
    -1.55
    윔
    -1.54
    ਗ
    -1.52
    ཿ
    -1.44
     grátis
    -1.44
    Сыртқы
    -1.43
    숱
    -1.41
    leté
    -1.41
    ·
    -1.41
    POSITIVE LOGITS
     before
    1.63
     хоть
    1.38
     x
    1.34
     then
    1.34
     at
    1.30
     while
    1.30
    したのは
    1.29
     only
    1.28
     from
    1.27
     after
    1.27
    Activations Density 0.001%

    No Known Activations