© 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. 31
    Prev
    Next
    INDEX
    Explanations

    or possible with

    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
     zijne
    -1.66
     古着
    -1.48
    に行って
    -1.48
     hunne
    -1.42
     terrific
    -1.34
    ようですが
    -1.32
     collega
    -1.30
    のでしょう
    -1.30
    のですか
    -1.24
    んでしょう
    -1.23
    POSITIVE LOGITS
     (
    1.77
     without
    1.45
     there
    1.45
     to
    1.38
    動物園
    1.36
    したので
    1.34
    してました
    1.32
     since
    1.30
    職人
    1.29
     for
    1.23
    Activations Density 0.036%

    No Known Activations