© 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. 67536
    Prev
    Next
    INDEX
    Explanations

    online computer operations

    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
    5
    -1.40
    8
    -1.38
    4
    -1.38
    を
    -1.31
    7
    -1.31
    が
    -1.26
    もしか
    -1.23
    据说
    -1.22
    6
    -1.22
     horrid
    -1.20
    POSITIVE LOGITS
     or
    1.54
     their
    1.28
    ocl
    1.23
     decidido
    1.23
    ujud
    1.23
     it
    1.23
     opravdu
    1.22
    matico
    1.22
    ليج
    1.21
     lentejuelas
    1.21
    Activations Density 0.098%

    No Known Activations