© 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. 119941
    Prev
    Next
    INDEX
    Explanations

    alleged wrongdoing

    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
     -
    -2.64
    蠖
    -2.31
    要不然
    -2.31
    癭
    -2.28
    ició
    -2.23
     و
    -2.06
    等我
    -2.05
    那你
    -1.98
    -1.98
    要不
    -1.97
    POSITIVE LOGITS
    ,“
    2.45
     touted
    2.30
     meticulous
    2.25
    s
    2.19
     steder
    2.17
     vermeld
    2.17
     måned
    2.16
     widespread
    2.09
    趼
    2.08
     henvis
    2.06
    Activations Density 0.002%

    No Known Activations