© 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. 8819
    Prev
    Next
    INDEX
    Explanations

    programming keywords and modifiers

    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
     colorear
    -1.65
     protectora
    -1.52
     barvy
    -1.51
     colorida
    -1.43
     aguj
    -1.39
     pracuje
    -1.38
     secado
    -1.35
    ༑
    -1.34
     filósofo
    -1.33
     skvě
    -1.32
    POSITIVE LOGITS
    k
    1.50
    </h2>
    1.47
     on
    1.39
    item
    1.30
    ars
    1.25
    ko
    1.24
    sel
    1.23
    z
    1.23
     I
    1.21
    ーツ
    1.20
    Activations Density 0.031%

    No Known Activations