© 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. 32646
    Prev
    Next
    INDEX
    Explanations

    spatial quantization and resolution

    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
     desenli
    -0.95
     encender
    -0.94
     use
    -0.90
    vle
    -0.89
     bubuk
    -0.86
    .
    -0.85
    RotationOrder
    -0.85
     from
    -0.85
     καν
    -0.84
    fever
    -0.83
    POSITIVE LOGITS
     neceff
    1.09
     نقاط
    0.98
    resolution
    0.96
    ścić
    0.95
    тература
    0.94
    chosen
    0.91
     prision
    0.90
     Nazare
    0.90
     neceffary
    0.89
    ariamente
    0.88
    Activations Density 0.030%

    No Known Activations