© 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. 22-GEMMASCOPE-RES-131K
    7. 104658
    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
     slå
    -1.19
     corporativa
    -1.16
    子が
    -1.16
     magnética
    -1.07
    леге
    -1.07
    клей
    -1.07
     reiz
    -1.07
    地看着
    -1.06
     их
    -1.02
    子の
    -1.02
    POSITIVE LOGITS
     our
    1.30
     veículo
    1.13
     riferimento
    1.13
     manchmal
    1.09
     racconto
    1.07
     sujeito
    1.06
     acidente
    1.05
    に似
    1.04
    に戻る
    1.04
     cuốn
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.