© 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. 10-GEMMASCOPE-RES-131K
    7. 123646
    Prev
    Next
    INDEX
    Explanations

    protection products and application

    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_10/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
     espirituales
    -1.63
     there
    -1.48
     rangka
    -1.42
     Новости
    -1.41
    っていますが
    -1.39
     Mungkin
    -1.38
    ventilador
    -1.38
     Meningkatkan
    -1.38
     čier
    -1.37
     Sebab
    -1.37
    POSITIVE LOGITS
     protect
    1.47
     such
    1.40
    */
    1.37
     good
    1.24
    を防
    1.19
     use
    1.19
    ↵↵↵
    1.11
    」
    1.10
     obblig
    1.10
    </
    1.10
    Activations Density 0.098%

    No Known Activations