© 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. 40159
    Prev
    Next
    INDEX
    Explanations

    useful things and solutions

    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
    kening
    -1.41
     continuación
    -1.23
     olie
    -1.17
     België
    -1.15
    FFECT
    -1.15
    éroport
    -1.13
    ffichage
    -1.12
    grees
    -1.11
    isling
    -1.10
     اللاعب
    -1.10
    POSITIVE LOGITS
     things
    2.28
     various
    1.69
     something
    1.64
     useful
    1.62
     everything
    1.62
     services
    1.54
     anything
    1.48
     everyday
    1.48
     helpful
    1.45
     solutions
    1.43
    Activations Density 0.045%

    No Known Activations