© 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. 81033
    Prev
    Next
    INDEX
    Explanations

    Q: or How to

    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
    Жан
    -0.86
     Guest
    -0.79
    predicate
    -0.77
     eating
    -0.76
     predicate
    -0.74
    ambah
    -0.74
    kult
    -0.73
     クリック
    -0.73
    getActivity
    -0.72
    アドレス
    -0.72
    POSITIVE LOGITS
     delinquency
    0.80
     quiver
    0.80
     xem
    0.79
     уход
    0.79
     Abdu
    0.78
    にならない
    0.75
    atalog
    0.75
     UNA
    0.75
     thank
    0.74
    thank
    0.73
    Activations Density 0.024%

    No Known Activations