© 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. 68813
    Prev
    Next
    INDEX
    Explanations

    I want

    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
     four
    -1.45
     three
    -1.42
     five
    -1.38
     ricas
    -1.35
     so
    -1.35
    十七
    -1.34
    ₇
    -1.33
     eight
    -1.32
     nine
    -1.32
     my
    -1.31
    POSITIVE LOGITS
    ꈍ
    1.49
     philippe
    1.46
    🫂
    1.45
     pernic
    1.44
     ficaram
    1.38
     illustratie
    1.38
     sentimentos
    1.37
     deverá
    1.34
    离去
    1.34
    🩹
    1.32
    Activations Density 0.006%

    No Known Activations