© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13465
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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
     to
    -2.03
     grim
    -1.66
     demandé
    -1.59
    ского
    -1.59
    ться
    -1.54
     poniendo
    -1.52
     którym
    -1.50
    nitus
    -1.47
    ēja
    -1.45
    irie
    -1.44
    POSITIVE LOGITS
    Two
    1.66
     but
    1.63
    Зміст
    1.59
    グルト
    1.52
     宣传
    1.48
    Through
    1.42
    Eight
    1.42
    Three
    1.41
    Four
    1.41
    Throughout
    1.41
    Activations Density 0.003%

    No Known Activations