© 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. 25727
    Prev
    Next
    INDEX
    Explanations

    predicting future outcomes or changes

    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
     merasa
    -1.00
     Lakukan
    -0.98
     spend
    -0.94
     experience
    -0.93
     enjoy
    -0.88
     abandon
    -0.87
     进行
    -0.85
     believe
    -0.84
     receive
    -0.84
     get
    -0.83
    POSITIVE LOGITS
    ทำให้
    1.18
     باعث
    1.13
     resulted
    1.06
     stanowi
    1.04
    ítja
    1.03
     enable
    1.03
    了不少
    1.01
     testifying
    0.97
     otwor
    0.96
    elts
    0.96
    Activations Density 0.066%

    No Known Activations