© 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. 58244
    Prev
    Next
    INDEX
    Explanations

    past tense verbs + followed by participles

    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
     naudoti
    -1.37
     etc
    -1.34
    ldots
    -1.34
    ğimiz
    -1.32
    órica
    -1.30
    bigli
    -1.30
    ngrx
    -1.27
    norme
    -1.26
    </h5>
    -1.25
     would
    -1.23
    POSITIVE LOGITS
     любой
    1.37
     was
    1.36
    慫
    1.29
    看了一眼
    1.27
    たまに
    1.22
    URS
    1.20
     between
    1.20
    】：
    1.20
     acabados
    1.19
    そんなに
    1.17
    Activations Density 0.211%

    No Known Activations