© 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. 70359
    Prev
    Next
    INDEX
    Explanations

    words and phrases

    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
     that
    -1.60
     it
    -1.22
     for
    -1.22
     when
    -1.21
     will
    -1.17
     then
    -1.11
     associated
    -1.10
     related
    -1.06
     during
    -1.06
    styrelsen
    -1.05
    POSITIVE LOGITS
    相変わらず
    1.29
     نیز
    1.21
     Cek
    1.16
     بھی
    1.14
     autonomie
    1.13
     ebenfalls
    1.13
    慙
    1.13
     тоже
    1.13
     plafond
    1.10
     ними
    1.09
    Activations Density 0.007%

    No Known Activations