© 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. 35819
    Prev
    Next
    INDEX
    Explanations

    purpose of academic work

    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
    Кстати
    -1.13
     alça
    -1.05
    事も
    -1.05
     preparo
    -1.02
     markiert
    -1.02
     huellas
    -1.00
     приводит
    -0.97
    捋
    -0.97
     требует
    -0.97
    Только
    -0.95
    POSITIVE LOGITS
     to
    2.03
     is
    1.34
    😫
    1.16
     είναι
    1.10
     purpose
    1.10
     in
    1.10
     adalah
    1.08
    🤤
    1.06
     цель
    1.06
     môžete
    1.03
    Activations Density 0.055%

    No Known Activations