© 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. 91584
    Prev
    Next
    INDEX
    Explanations

    Open Source License 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
    image
    -0.70
    clock
    -0.64
     Pollo
    -0.63
    ื่อน
    -0.62
    koda
    -0.62
     sva
    -0.62
    baño
    -0.61
    crash
    -0.60
    identify
    -0.60
     tahan
    -0.59
    POSITIVE LOGITS
    ungeon
    0.75
    ◤
    0.74
     deposit
    0.71
    笹
    0.70
    𝟸
    0.69
    困难
    0.69
     maternal
    0.69
    צר
    0.68
    Toxicity
    0.68
    ္
    0.67
    Activations Density 0.073%

    No Known Activations