© 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. 34-GEMMASCOPE-RES-131K
    7. 107393
    Prev
    Next
    INDEX
    Explanations

    saving data or objects

    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
    storage
    -0.90
    operatorname
    -0.86
     getUsers
    -0.84
     zapach
    -0.84
     RouterModule
    -0.79
    Coll
    -0.78
    TextEditing
    -0.77
    match
    -0.76
     kabar
    -0.75
     keju
    -0.75
    POSITIVE LOGITS
     save
    1.19
     Save
    0.99
     without
    0.92
     saves
    0.88
     SAVE
    0.83
    幸いです
    0.81
    save
    0.81
    Save
    0.80
     saving
    0.77
    nobyl
    0.77
    Activations Density 0.004%

    No Known Activations