© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34824
    Prev
    Next
    INDEX
    Explanations

    linear gradient or xor

    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_34/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
     Geschlecht
    -0.71
     klasy
    -0.67
     Dienstag
    -0.67
    само
    -0.64
     publicKey
    -0.64
     Colleges
    -0.62
     ecuador
    -0.62
     爱
    -0.62
    ToggleButton
    -0.62
    ️
    -0.60
    POSITIVE LOGITS
     pocit
    0.71
    leville
    0.70
     progrès
    0.67
    Sushi
    0.67
    getFullYear
    0.67
    结束后
    0.66
     Venetian
    0.66
    Maritime
    0.65
     subtract
    0.65
     sạn
    0.65
    Activations Density 0.058%

    No Known Activations