© 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. 38790
    Prev
    Next
    INDEX
    Explanations

    aesthetic and artistic design

    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
    ּוֹ
    -1.98
    ַּ
    -1.49
     bandoulière
    -1.47
    ִּ
    -1.30
    tigma
    -1.21
     lidé
    -1.17
    しましたが
    -1.16
    ֶּ
    -1.16
    ဤ
    -1.15
    してた
    -1.13
    POSITIVE LOGITS
    ׇ
    1.35
     художе
    1.23
     aesthetic
    1.20
     artistic
    1.13
     design
    1.12
     creative
    1.09
     aesthetics
    1.07
    It
    1.07
    I
    1.05
    You
    1.04
    Activations Density 0.183%

    No Known Activations