© 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. 356
    Prev
    Next
    INDEX
    Explanations

    cockpit or tkinter

    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
    氿
    -2.61
    랬
    -2.53
     потім
    -2.30
    泚
    -2.30
     دیدار
    -2.30
    ዑ
    -2.30
    </h4>
    -2.28
     mehrere
    -2.23
     smelly
    -2.20
    辄
    -2.19
    POSITIVE LOGITS
    (
    2.45
    蹋
    2.27
     kutoka
    2.13
    賔
    2.11
     puteți
    2.02
     ænd
    2.00
    褡
    1.98
    蹰
    1.92
    たと
    1.91
    I
    1.91
    Activations Density 0.006%

    No Known Activations