© 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. 35704
    Prev
    Next
    INDEX
    Explanations

    HTML structure elements

    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
    Estou
    -0.93
    ďte
    -0.92
     deberá
    -0.89
    écu
    -0.89
    uszka
    -0.88
    saat
    -0.87
    endaten
    -0.86
     informacija
    -0.85
    wska
    -0.85
    énieurs
    -0.85
    POSITIVE LOGITS
     two
    1.00
     beckon
    1.00
     meu
    0.84
     jedno
    0.83
     -
    0.82
     Bloem
    0.81
    #
    0.80
    ਇ
    0.79
    )++;
    0.79
     --
    0.79
    Activations Density 0.005%

    No Known Activations