© 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. 13447
    Prev
    Next
    INDEX
    Explanations

    type assignments

    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
    Արտաքին
    -1.15
     when
    -1.15
     with
    -1.03
    Hopefully
    -0.99
     katkıda
    -0.96
     going
    -0.96
    Groetjes
    -0.95
    titial
    -0.94
     why
    -0.93
     function
    -0.91
    POSITIVE LOGITS
    CEAN
    1.09
    ITY
    0.96
     Weasley
    0.93
    tipo
    0.93
    craina
    0.92
     '-';
    0.92
     naturaleza
    0.91
     både
    0.91
     tyran
    0.91
     тип
    0.91
    Activations Density 0.021%

    No Known Activations