© 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. 22-GEMMASCOPE-RES-131K
    7. 70691
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, questions

    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_22/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
     Grüßen
    -1.20
    罰
    -1.05
    iteritems
    -1.05
    mtliche
    -1.04
     Prou
    -1.02
    災害
    -1.01
    ₫
    -1.00
    wester
    -0.98
    ulação
    -0.97
     її
    -0.96
    POSITIVE LOGITS
    凄く
    1.05
    昔から
    1.02
    なかな
    1.02
     находятся
    1.02
    いけ
    1.00
     женская
    0.99
     esfuer
    0.96
    ところは
    0.95
     gesehen
    0.94
     システム
    0.94
    Activations Density 0.018%

    No Known Activations