© 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. 28647
    Prev
    Next
    INDEX
    Explanations

    starting a question or news item about technical topics

    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
     Pfar
    -1.30
    ἵ
    -1.27
    cccccccc
    -1.27
     Hinweis
    -1.26
    ׇ
    -1.25
     BUT
    -1.24
     maroca
    -1.23
    𝑈
    -1.20
     religieuse
    -1.19
     katholischen
    -1.19
    POSITIVE LOGITS
    ַּ
    1.53
    ּוֹ
    1.48
    וּ
    1.39
    ִּ
    1.36
     mantenga
    1.24
     resource
    1.23
     herinner
    1.21
     vertrou
    1.20
     surfact
    1.18
     voldo
    1.17
    Activations Density 0.011%

    No Known Activations