© 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. 16524
    Prev
    Next
    INDEX
    Explanations

    options and alternatives

    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
    inals
    -0.89
    chtig
    -0.83
     induct
    -0.80
     dieselben
    -0.79
    において
    -0.78
    平均
    -0.78
    Mongo
    -0.77
    CADE
    -0.76
    mino
    -0.76
    Controls
    -0.76
    POSITIVE LOGITS
     options
    2.30
     possibilities
    1.88
     available
    1.76
     alternatives
    1.73
     possible
    1.60
     choices
    1.45
     suitable
    1.41
     Möglichkeiten
    1.35
     suggestions
    1.34
     можли
    1.34
    Activations Density 0.145%

    No Known Activations