© 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. 10-GEMMASCOPE-RES-131K
    7. 65465
    Prev
    Next
    INDEX
    Explanations

    still remains

    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_10/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
     with
    -1.52
     również
    -1.34
    Život
    -1.33
     уже
    -1.26
    ↵↵
    -1.25
    шники
    -1.23
     совсем
    -1.21
     during
    -1.21
    mış
    -1.20
     before
    -1.20
    POSITIVE LOGITS
    やっぱ
    1.77
    begin
    1.59
     viewDidLoad
    1.47
    の存在
    1.45
     maioria
    1.41
    .):
    1.41
     occuper
    1.40
    ⢪
    1.38
     who
    1.37
    基本的に
    1.37
    Activations Density 0.031%

    No Known Activations