© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57313
    Prev
    Next
    INDEX
    Explanations

    lifestyle magazines and content

    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
     Huss
    -0.79
    么
    -0.78
     it
    -0.76
    LB
    -0.75
    olé
    -0.74
    iense
    -0.72
     WEDNESDAY
    -0.72
    九月
    -0.72
     Mrs
    -0.71
    др
    -0.71
    POSITIVE LOGITS
    SHOP
    0.86
    縞
    0.77
     Hearst
    0.77
     quête
    0.76
    ceiro
    0.73
    没人
    0.71
    ^{(\
    0.71
    IMPORTED
    0.71
     seleccionado
    0.71
    {%
    0.70
    Activations Density 0.013%

    No Known Activations