© 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. 43084
    Prev
    Next
    INDEX
    Explanations

    acting quickly

    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
    </strong>
    -3.59
     zwölf
    -2.66
     fervent
    -2.48
     immense
    -2.44
     astute
    -2.36
     

    -2.36
     solch
    -2.34
     impromptu
    -2.33
    ↵
    -2.30
     ursprünglich
    -2.25
    POSITIVE LOGITS
     italia
    2.89
     storie
    2.73
     stile
    2.66
     سازی
    2.63
     milano
    2.63
    豋
    2.52
    禑
    2.50
     venezia
    2.45
    婞
    2.38
     riso
    2.36
    Activations Density 0.000%

    No Known Activations