© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59154
    Prev
    Next
    INDEX
    Explanations

    foreign words and historical dates

    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
     their
    -1.82
     other
    -1.72
     how
    -1.59
     there
    -1.54
     related
    -1.48
     others
    -1.46
     new
    -1.42
    rabbitmq
    -1.41
     possible
    -1.34
     newer
    -1.34
    POSITIVE LOGITS
    着一个
    1.38
     jedoch
    1.36
     voiture
    1.23
     gratuits
    1.23
     cheveux
    1.18
     privés
    1.13
    moke
    1.13
    ᄉ
    1.11
    】:
    1.11
     allerdings
    1.09
    Activations Density 0.089%

    No Known Activations