© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110703
    Prev
    Next
    INDEX
    Explanations

    ability to manage or withstand

    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_34/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
    ất
    -0.98
    —¡
    -0.79
     punya
    -0.77
    })->
    -0.73
     gestos
    -0.73
    👔
    -0.73
    oides
    -0.71
    tować
    -0.71
     sleeps
    -0.70
     Lyons
    -0.69
    POSITIVE LOGITS
     handle
    5.19
    handle
    4.19
     handles
    4.13
     handling
    4.13
     Handle
    3.91
     handled
    3.89
    Handle
    3.59
     Handling
    3.36
    Handling
    3.27
     Handles
    3.20
    Activations Density 0.056%

    No Known Activations