© 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. 22-GEMMASCOPE-RES-131K
    7. 12523
    Prev
    Next
    INDEX
    Explanations

    locations and translations

    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
     but
    -1.22
    omaly
    -1.01
    いましたが
    -0.98
     addirittura
    -0.92
     pouvez
    -0.91
    inado
    -0.89
    bano
    -0.87
    Personendaten
    -0.87
    NÉ
    -0.87
     gdyż
    -0.86
    POSITIVE LOGITS
    hôpital
    0.94
    ambassade
    0.93
    Introducción
    0.90
    Traducción
    0.88
     oba
    0.88
     drapery
    0.88
    appartement
    0.86
    mandu
    0.85
    Toeschouwers
    0.85
    hébergement
    0.85
    Activations Density 0.183%

    No Known Activations