© 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. 60489
    Prev
    Next
    INDEX
    Explanations

    about the

    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
     oppervlak
    -1.83
     vloer
    -1.66
     After
    -1.65
     cuando
    -1.61
     very
    -1.60
     When
    -1.59
     cilindros
    -1.57
     voed
    -1.52
     mijne
    -1.48
     and
    -1.46
    POSITIVE LOGITS
    Deine
    1.47
    真的好
    1.45
     bardziej
    1.43
     harten
    1.41
     основных
    1.41
    jut
    1.41
    最近は
    1.40
    breos
    1.40
    Externe
    1.36
     публикации
    1.36
    Activations Density 0.053%

    No Known Activations