© 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. 13176
    Prev
    Next
    INDEX
    Explanations

    if you

    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
     boute
    -1.17
     元素
    -1.13
     suspic
    -1.09
     ilu
    -1.08
     gril
    -1.06
     parfum
    -1.06
     errone
    -1.05
     babi
    -1.05
     prodi
    -1.04
     vagab
    -1.03
    POSITIVE LOGITS
     you
    1.54
     which
    1.23
     there
    1.12
     like
    1.02
     that
    1.02
    '.
    1.00
     которые
    0.99
     cần
    0.96
     don
    0.96
    家を
    0.95
    Activations Density 0.013%

    No Known Activations