© 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. 114122
    Prev
    Next
    INDEX
    Explanations

    this is/are/was/were constructions

    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
    antaranya
    -1.40
    goes
    -1.38
    뻥
    -1.36
     reunião
    -1.34
    endaten
    -1.30
    簠
    -1.29
    ówka
    -1.29
     ボード
    -1.28
     apropri
    -1.27
    ciful
    -1.25
    POSITIVE LOGITS
     and
    1.36
     first
    1.36
     when
    1.33
     gave
    1.25
     create
    1.25
     before
    1.24
     WITH
    1.23
     created
    1.20
     seems
    1.19
     generated
    1.19
    Activations Density 0.031%

    No Known Activations