© 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. 74582
    Prev
    Next
    INDEX
    Explanations

    so followed by consequence

    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
     vilja
    -1.48
     Numerous
    -1.48
    主要是
    -1.48
     fhall
    -1.43
    整个
    -1.38
     bahwa
    -1.38
    tellten
    -1.38
     kollu
    -1.38
    ⃣
    -1.35
     egenskaper
    -1.34
    POSITIVE LOGITS
     другую
    1.48
     of
    1.41
    的事情
    1.36
    了什么
    1.30
    ৄ
    1.30
    一旁
    1.27
    ’
    1.27
    了你
    1.27
    があれば
    1.25
     Municipalidad
    1.24
    Activations Density 0.039%

    No Known Activations