© 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. 103447
    Prev
    Next
    INDEX
    Explanations

    javascript DOM manipulation

    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
    Osp
    -0.96
    査
    -0.82
    !
    -0.71
     (*(
    -0.69
     что
    -0.67
    례
    -0.67
    歪
    -0.66
     IVF
    -0.66
    네
    -0.66
    原料
    -0.65
    POSITIVE LOGITS
    document
    1.55
    getElementById
    1.49
     document
    1.45
    innerHTML
    1.22
    onclick
    1.13
    alert
    1.10
     prompt
    1.07
     onclick
    1.03
     alert
    1.03
     getElement
    1.02
    Activations Density 0.075%

    No Known Activations