© 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. 10-GEMMASCOPE-RES-131K
    7. 130461
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    ↵
    -1.69
     of
    -1.54
    ',
    -1.52
     to
    -1.49
    、
    -1.43
     my
    -1.41
     at
    -1.38
     –
    -1.34
     your
    -1.34
    ",
    -1.34
    POSITIVE LOGITS
     když
    1.55
    cuando
    1.49
    向けの
    1.40
    meleri
    1.34
     vendu
    1.32
    行业的
    1.27
     takže
    1.26
     véhic
    1.23
     când
    1.23
     polaire
    1.23
    Activations Density 0.011%

    No Known Activations