© 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. 93522
    Prev
    Next
    INDEX
    Explanations

    addresses and copyright notices

    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
     sztuki
    -0.84
     hồi
    -0.82
     Bucure
    -0.80
     concentrated
    -0.80
    签订
    -0.79
     Uniwers
    -0.78
    過ぎて
    -0.77
    ového
    -0.77
    ukset
    -0.77
     sections
    -0.77
    POSITIVE LOGITS
     ATLAS
    1.09
     ofte
    0.90
    quote
    0.86
    ATLAS
    0.86
    :',
    0.83
    納豆
    0.83
    orithms
    0.80
    去年
    0.79
     POW
    0.78
    ӧ
    0.78
    Activations Density 0.000%

    No Known Activations