© 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. 109614
    Prev
    Next
    INDEX
    Explanations

    save money and time

    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
    Stolen
    -0.93
    Funded
    -0.90
     oub
    -0.88
     filmp
    -0.88
    meldung
    -0.86
     cire
    -0.83
    gelijke
    -0.82
    ſa
    -0.82
    gorov
    -0.81
     perle
    -0.80
    POSITIVE LOGITS
     money
    2.06
     time
    1.80
     on
    1.48
    money
    1.40
     both
    1.30
    Save
    1.25
     save
    1.23
     saves
    1.22
     Money
    1.21
     considerable
    1.14
    Activations Density 0.012%

    No Known Activations