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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15694
    Prev
    Next
    INDEX
    Explanations

    comparative quantities or levels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Erkenntnis
    -1.10
    Polska
    -1.02
     altres
    -1.02
    ()],
    -1.01
     resep
    -1.01
    layed
    -1.00
    ított
    -0.99
     flexível
    -0.99
    ATIVES
    -0.98
     姉
    -0.98
    POSITIVE LOGITS
     amount
    1.16
     amounts
    1.16
    T
    1.02
     proportion
    1.01
     alludes
    0.95
    ber
    0.95
    R
    0.93
     conveys
    0.91
     atunci
    0.88
     different
    0.88
    Activations Density 0.077%

    No Known Activations