© 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. 83280
    Prev
    Next
    INDEX
    Explanations

    file paths and copyright information

    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
    rits
    -0.72
    撕
    -0.69
     Machines
    -0.69
    teal
    -0.69
    conom
    -0.68
     Machine
    -0.68
    celebr
    -0.68
    Ầ
    -0.67
    rigo
    -0.67
     roze
    -0.66
    POSITIVE LOGITS
    Lew
    0.82
    umar
    0.72
     Campo
    0.69
     Moya
    0.69
    Ꮯ
    0.67
    dited
    0.66
    sify
    0.66
     objs
    0.65
    最后
    0.65
     disclose
    0.65
    Activations Density 0.066%

    No Known Activations