© 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. 22-GEMMASCOPE-RES-131K
    7. 14343
    Prev
    Next
    INDEX
    Explanations

    license

    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
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.15
     by
    -1.13
     You
    -1.09
    ほうが
    -1.05
    ノベーション
    -1.05
    側は
    -1.03
     [
    -1.02
    пса
    -1.00
    用に
    -0.99
    のこ
    -0.99
    POSITIVE LOGITS
    Hilsen
    1.32
     oxígeno
    1.13
    توضیحات
    1.13
     caucho
    1.11
    خخ
    1.11
    معرفی
    1.11
     colegios
    1.10
    ἐ
    1.10
     hornear
    1.09
    Livraison
    1.09
    Activations Density 0.001%

    No Known Activations