© 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. 106248
    Prev
    Next
    INDEX
    Explanations

    database field definitions

    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
    HasColumn
    -0.85
    EXO
    -0.81
    𝗷
    -0.80
    ティー
    -0.80
     zirc
    -0.79
     clavic
    -0.79
    Fallen
    -0.78
    Доброго
    -0.78
     Ryzen
    -0.78
     Bautista
    -0.78
    POSITIVE LOGITS
     field
    1.20
     Model
    0.96
    field
    0.94
     allow
    0.93
    Model
    0.86
    allowNull
    0.82
     permitir
    0.81
     model
    0.80
     unique
    0.80
    Field
    0.78
    Activations Density 0.002%

    No Known Activations