© 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. 77131
    Prev
    Next
    INDEX
    Explanations

    DOM manipulation functions

    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
     that
    -0.88
    strum
    -0.87
    xlarge
    -0.81
    órum
    -0.79
     of
    -0.78
    льне
    -0.76
    了一会儿
    -0.76
    借
    -0.76
    也能
    -0.74
    ванные
    -0.74
    POSITIVE LOGITS
    hide
    1.19
     hide
    1.11
    html
    1.07
    show
    1.02
     html
    1.01
    Biblia
    0.96
     hijos
    0.95
     tomber
    0.94
     SHOW
    0.92
     siir
    0.92
    Activations Density 0.012%

    No Known Activations