© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129838
    Prev
    Next
    INDEX
    Explanations

    person's name

    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
     it
    -1.48
     this
    -1.48
     probably
    -1.41
    ter
    -1.39
    </h4>
    -1.35
    Â
    -1.35
    中の
    -1.33
    s
    -1.32
     If
    -1.27
     At
    -1.23
    POSITIVE LOGITS
     who
    1.67
    kệ
    1.49
    pollution
    1.43
     แปล
    1.42
    Carex
    1.40
    糹
    1.38
    🫂
    1.38
     barev
    1.38
     getName
    1.33
    estimable
    1.31
    Activations Density 0.058%

    No Known Activations