© 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. 13075
    Prev
    Next
    INDEX
    Explanations

    listen carefully, pay attention

    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
     другие
    -1.48
     andere
    -1.47
     ocen
    -1.40
     cortada
    -1.39
    varlak
    -1.38
     consummate
    -1.36
    ↵
    -1.36
     tailor
    -1.32
     meget
    -1.30
    怔
    -1.29
    POSITIVE LOGITS
    .,"
    1.45
    ">(</
    1.43
    couraged
    1.42
     although
    1.41
    icação
    1.38
     their
    1.36
    ()),
    1.33
    listen
    1.32
    </h3>
    1.31
    xically
    1.30
    Activations Density 0.020%

    No Known Activations