© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 28962
    Prev
    Next
    INDEX
    Explanations

    JHipster project, Vodafone, Q:, #include, Experimental studies

    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_10/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
     gastronomía
    -1.80
     their
    -1.73
     from
    -1.66
     Fahrzeuge
    -1.64
     esquí
    -1.62
    dsquared
    -1.60
     cómoda
    -1.59
    explique
    -1.55
    Válasz
    -1.53
     teléfonos
    -1.53
    POSITIVE LOGITS
     but
    1.96
     InputMaybe
    1.52
    quisition
    1.41
    стях
    1.41
    ші
    1.41
    lograph
    1.38
    ство
    1.38
    是啊
    1.35
     иногда
    1.35
    thirds
    1.35
    Activations Density 0.001%

    No Known Activations