© 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. 67433
    Prev
    Next
    INDEX
    Explanations

    condiments, spices, powders

    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
    衚
    -1.68
    ývá
    -1.63
    ).”
    -1.59
    这就是
    -1.59
    已经在
    -1.58
    描く
    -1.58
    crania
    -1.57
     “
    -1.56
     людьми
    -1.55
    −/−
    -1.55
    POSITIVE LOGITS
    ти
    1.84
    )
    1.65
    ꔹ
    1.64
    ваш
    1.63
     interesan
    1.62
    附属
    1.60
    ка
    1.58
    dafx
    1.54
     Ди
    1.48
     construit
    1.48
    Activations Density 0.006%

    No Known Activations