© 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. 10-GEMMASCOPE-RES-131K
    7. 86484
    Prev
    Next
    INDEX
    Explanations

    money and spending

    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_10/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
     voile
    -1.32
     entendre
    -1.27
    </h4>
    -1.19
     curé
    -1.18
     bons
    -1.18
     bara
    -1.17
     belles
    -1.16
    "
    -1.16
    Predecesor
    -1.16
     のみ
    -1.14
    POSITIVE LOGITS
    anganese
    1.39
     laajenta
    1.36
    ᎑
    1.31
     vähän
    1.30
    ڡ
    1.29
     kautta
    1.27
     sobě
    1.25
     tekem
    1.23
     kuiten
    1.22
     todays
    1.20
    Activations Density 0.062%

    No Known Activations