© 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. 37901
    Prev
    Next
    INDEX
    Explanations

    say or describe words

    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
    ſ
    -0.75
    owany
    -0.75
    водов
    -0.73
    ȯ
    -0.71
     Komun
    -0.71
     принтом
    -0.70
     иногда
    -0.69
    vantaged
    -0.68
     ejemplos
    -0.68
    𝑡
    -0.67
    POSITIVE LOGITS
     colours
    1.47
     numbers
    1.45
     colors
    1.44
     greetings
    1.43
     clothing
    1.25
     clothes
    1.20
    colors
    1.18
     Numbers
    1.17
     food
    1.16
     animals
    1.14
    Activations Density 0.038%

    No Known Activations