© 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. 40312
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    asztal
    -1.31
     maquillage
    -1.27
     lavabo
    -1.27
    zdo
    -1.23
     comté
    -1.20
     biela
    -1.20
    >(_
    -1.20
    viève
    -1.20
     État
    -1.20
     camisas
    -1.19
    POSITIVE LOGITS
    u
    1.49
    ar
    1.40
    is
    1.37
    on
    1.36
    j
    1.32
    al
    1.30
    na
    1.28
    l
    1.27
    i
    1.25
    at
    1.23
    Activations Density 0.001%

    No Known Activations