© 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. 22-GEMMASCOPE-RES-131K
    7. 16651
    Prev
    Next
    INDEX
    Explanations

    code: `contains` `and` `extension`

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     on
    -0.94
    гій
    -0.89
    Suka
    -0.88
    NSUserDefaults
    -0.87
     Fill
    -0.85
     kondisi
    -0.83
    motif
    -0.82
     next
    -0.82
    ímp
    -0.82
     бел
    -0.81
    POSITIVE LOGITS
    WEBPACK
    0.90
     ২০১
    0.87
     représentant
    0.86
     таке
    0.86
     représentants
    0.84
    巻き
    0.82
    同样的
    0.82
    查詢
    0.81
     cance
    0.81
     Winding
    0.80
    Activations Density 0.009%

    No Known Activations