© 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. 27377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    🔥🔥
    -1.34
     ❤️❤️
    -1.33
     😍😍
    -1.32
     🖤
    -1.27
    ❤️❤️
    -1.26
     💗
    -1.26
    💓
    -1.26
    ☺☺
    -1.25
    ❣
    -1.23
     ❓
    -1.22
    POSITIVE LOGITS
    acité
    1.09
     recklessly
    1.07
    棕色
    1.07
    ⾞
    1.02
    約
    1.02
     аудио
    1.02
    acterium
    1.02
    inalis
    1.01
    少し
    1.01
     également
    1.01
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.