© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64533
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     this
    -0.99
     was
    -0.99
     after
    -0.98
    ورده
    -0.93
    InputBorder
    -0.93
    はこの
    -0.92
    🤙
    -0.91
     чувства
    -0.89
    توضیحات
    -0.89
    🤯
    -0.88
    POSITIVE LOGITS
    就可以了
    1.17
     bewilder
    1.03
     unending
    1.03
     хуже
    1.03
     Ně
    1.02
    Increases
    1.00
    才可以
    1.00
     thre
    0.99
     крупных
    0.99
     جمعه
    0.99
    Activations Density 0.176%

    No Known Activations