© 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. 34-GEMMASCOPE-RES-131K
    7. 50073
    Prev
    Next
    INDEX
    Explanations

    numerical bases

    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_34/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
     Sabtu
    -0.76
     engraçadas
    -0.76
    举行
    -0.69
    İyi
    -0.69
    quartile
    -0.68
     zapro
    -0.67
    cedure
    -0.67
    ılması
    -0.66
     rebajas
    -0.65
     either
    -0.65
    POSITIVE LOGITS
     base
    1.71
     Base
    1.57
    Base
    1.56
     radix
    1.50
     binary
    1.48
    base
    1.46
     BASE
    1.42
     sistema
    1.34
    BASE
    1.34
     bases
    1.34
    Activations Density 0.045%

    No Known Activations