© 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. 35774
    Prev
    Next
    INDEX
    Explanations

    domain identifiers and their qualifiers

    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
    あぁ
    -1.48
    parka
    -1.28
    えっ
    -1.28
    ほら
    -1.24
    おわりに
    -1.23
     équilibr
    -1.22
     dél
    -1.20
     betyder
    -1.17
    総評
    -1.16
    labas
    -1.16
    POSITIVE LOGITS
     situation
    1.34
     situations
    1.20
     items
    1.20
     stuff
    1.18
    section
    1.16
    r
    1.16
    specific
    1.16
     mostly
    1.15
     cases
    1.07
     although
    1.05
    Activations Density 0.124%

    No Known Activations