© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6865
    Prev
    Next
    INDEX
    Explanations

    transition words

    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
    Negative Logits
     you
    -1.68
     by
    -1.46
    ৄ
    -1.33
     Tampa
    -1.29
    戗
    -1.26
     außerhalb
    -1.25
     irgend
    -1.24
     use
    -1.24
     denselben
    -1.22
     Dublin
    -1.20
    POSITIVE LOGITS
    かは
    1.38
    如此
    1.33
     such
    1.32
     приходится
    1.30
    Situated
    1.28
    such
    1.22
    responses
    1.19
     exhi
    1.17
    zett
    1.16
    ilets
    1.16
    Activations Density 0.084%

    No Known Activations