© 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. 34-GEMMASCOPE-RES-131K
    7. 12100
    Prev
    Next
    INDEX
    Explanations

    image url or file name

    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
     olisi
    -0.73
    вающий
    -0.69
     Artistic
    -0.69
     cidades
    -0.66
     dáms
    -0.66
     honoured
    -0.66
    arm
    -0.66
    interceptors
    -0.65
    इस
    -0.65
    unzip
    -0.65
    POSITIVE LOGITS
    IMG
    2.53
     IMG
    1.70
     Img
    0.95
    Img
    0.80
    forts
    0.80
    stine
    0.78
    initely
    0.76
    캬
    0.75
    img
    0.74
     img
    0.73
    Activations Density 0.049%

    No Known Activations