© 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. 70601
    Prev
    Next
    INDEX
    Explanations

    numbers, IDs, and debug information

    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
     while
    -1.91
     during
    -1.86
     this
    -1.86
     their
    -1.78
     for
    -1.57
     before
    -1.51
     its
    -1.49
     or
    -1.48
     when
    -1.48
     after
    -1.48
    POSITIVE LOGITS
    は
    1.51
    珰
    1.43
    卺
    1.42
    usually
    1.34
    鲞
    1.34
    became
    1.34
    knew
    1.33
    킁
    1.26
    盉
    1.26
    Pokud
    1.24
    Activations Density 0.004%

    No Known Activations