© 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. 34-GEMMASCOPE-RES-131K
    7. 106119
    Prev
    Next
    INDEX
    Explanations

    would have + past participle

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    så
    -1.12
    鳚
    -1.11
     capitulo
    -1.10
     excès
    -1.09
     répondu
    -1.05
    䛗
    -1.05
    eamiento
    -1.04
    𝕱
    -1.04
     ceremonia
    -1.04
    digkeit
    -1.04
    POSITIVE LOGITS
     been
    2.30
     expected
    1.51
     gotten
    1.35
     had
    1.32
     needed
    1.26
     known
    1.24
     existed
    1.17
     gewesen
    1.16
     originally
    1.13
     hoped
    1.13
    Activations Density 0.026%

    No Known Activations