© 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. 66178
    Prev
    Next
    INDEX
    Explanations

    long ago, same, same time

    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
     is
    -1.49
    Decided
    -1.43
    Så
    -1.41
    rawn
    -1.30
     стоимо
    -1.30
    尤其是
    -1.22
    to
    -1.20
    を越
    -1.20
    <i>
    -1.19
    appcompat
    -1.18
    POSITIVE LOGITS
     phiếu
    1.39
    もありました
    1.38
     same
    1.38
    的气息
    1.37
     of
    1.35
     sereia
    1.33
    も同じ
    1.31
     pareil
    1.30
     đáo
    1.29
    uniqlo
    1.29
    Activations Density 0.030%

    No Known Activations