© 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. 3426
    Prev
    Next
    INDEX
    Explanations

    would appear, would be, would have

    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
    荭
    -1.13
     xxiii
    -1.09
    靓
    -1.00
    aneity
    -0.99
     使っ
    -0.99
    中には
    -0.97
    eping
    -0.94
    meye
    -0.93
    Вот
    -0.92
    tière
    -0.92
    POSITIVE LOGITS
     seem
    2.44
     be
    2.34
    Seems
    1.71
    seem
    1.68
     have
    1.62
     appear
    1.55
     Seems
    1.55
     not
    1.45
    seems
    1.45
     lijkt
    1.44
    Activations Density 0.032%

    No Known Activations