© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109499
    Prev
    Next
    INDEX
    Explanations

    dates and paths

    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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.85
     Quadrat
    -0.84
     relating
    -0.84
    locationManager
    -0.83
     coorden
    -0.82
     tenure
    -0.81
    frontmatter
    -0.81
     vital
    -0.79
     fully
    -0.79
     half
    -0.78
    POSITIVE LOGITS
    ∕
    1.03
    /
    0.91
     victoires
    0.89
    λους
    0.88
    envie
    0.86
    apparence
    0.83
     '/
    0.83
    \/
    0.82
    uscht
    0.82
    sandalias
    0.80
    Activations Density 0.063%

    No Known Activations