© 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. 90935
    Prev
    Next
    INDEX
    Explanations

    making easier or possible

    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
     boissons
    -0.92
    充滿
    -0.87
    "}";
    -0.84
     ganadores
    -0.84
     kombiniert
    -0.83
    adería
    -0.83
    ꯖ
    -0.82
     estuche
    -0.82
     suscripción
    -0.81
    kang
    -0.80
    POSITIVE LOGITS
     facilitate
    3.97
     easier
    3.91
     facilitar
    3.80
     facilitates
    3.58
     facilitating
    3.47
     ease
    3.36
     simplify
    3.28
     Facilit
    3.28
     memudahkan
    3.27
     simplifies
    3.22
    Activations Density 0.267%

    No Known Activations