© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1741
    Prev
    Next
    INDEX
    Explanations

    image or avatar

    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
    蘭
    -0.77
    氏
    -0.73
    니까
    -0.71
    標
    -0.71
    вай
    -0.70
     alphabets
    -0.70
     NBS
    -0.70
    MPEG
    -0.69
    onik
    -0.69
     Galax
    -0.68
    POSITIVE LOGITS
     pic
    0.99
    local
    0.95
     PIC
    0.92
    oss
    0.91
    pic
    0.91
    ImageView
    0.90
     picture
    0.88
     local
    0.84
     pictures
    0.84
     Pic
    0.82
    Activations Density 0.010%

    No Known Activations