© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26868
    Prev
    Next
    INDEX
    Explanations

    spend time or money

    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_22/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
     that
    -1.50
     Things
    -1.16
     continue
    -1.11
     what
    -1.10
     being
    -1.10
     when
    -1.09
     having
    -1.07
     only
    -1.07
     also
    -1.05
     behavior
    -1.03
    POSITIVE LOGITS
     forment
    1.13
    ΰ
    1.05
    spent
    1.03
    Spend
    0.96
    utriche
    0.95
     Seperti
    0.93
    spend
    0.92
     utro
    0.92
    เวลา
    0.91
     glade
    0.89
    Activations Density 0.035%

    No Known Activations