© 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. 40097
    Prev
    Next
    INDEX
    Explanations

    how something is done

    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
     pokud
    -1.09
    りましたが
    -0.99
     fallecido
    -0.97
    atellite
    -0.96
     terá
    -0.94
    ConstraintMaker
    -0.93
    Pontos
    -0.92
     câteva
    -0.92
     toekomst
    -0.92
    Liefs
    -0.91
    POSITIVE LOGITS
     to
    1.29
    どうやって
    1.29
     method
    1.23
    的方法
    1.11
     process
    1.07
     manage
    1.05
     methods
    1.05
     achieve
    1.02
    取得
    0.98
     mechanism
    0.98
    Activations Density 0.110%

    No Known Activations