© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48566
    Prev
    Next
    INDEX
    Explanations

    fetch or retrieve

    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
    spend
    -0.93
    addImage
    -0.81
    addProduct
    -0.79
    Taxonomy
    -0.76
    artigen
    -0.76
    springen
    -0.76
    metodo
    -0.75
    bedür
    -0.75
    Inbox
    -0.75
    zeitig
    -0.74
    POSITIVE LOGITS
     fetch
    3.27
     fetching
    2.94
    fetch
    2.78
     fetched
    2.70
    Fetch
    2.45
     Fetch
    2.38
     retrieving
    2.06
     retrieve
    2.05
     FETCH
    1.92
     retrieval
    1.90
    Activations Density 0.018%

    No Known Activations