© 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. 28142
    Prev
    Next
    INDEX
    Explanations

    word or character limit

    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
     inapropiados
    -1.24
     other
    -1.21
    ζει
    -1.15
    According
    -1.10
    remot
    -1.06
     ویتامین
    -1.06
    tuesday
    -1.06
    茈
    -1.05
     déclare
    -1.05
     mencionados
    -1.05
    POSITIVE LOGITS
     about
    1.87
    öße
    1.47
     aproximadamente
    1.38
     cualquier
    1.30
     qualquer
    1.24
    ประมาณ
    1.24
     your
    1.21
     roughly
    1.16
     approximately
    1.13
     "}";
    1.07
    Activations Density 0.011%

    No Known Activations