© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 1016
    Prev
    Next
    INDEX
    Explanations

    legal testimony

    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
    趼
    -2.77
    迓
    -2.56
    矜
    -2.38
    枷
    -2.38
     jenem
    -2.34
    AutoresizingMask
    -2.31
    lognese
    -2.27
    FormUrlEncoded
    -2.27
    ları
    -2.25
     *
    -2.22
    POSITIVE LOGITS
    栳
    3.08
    涐
    2.88
    榀
    2.75
    獴
    2.58
     یه
    2.56
    葙
    2.55
    0
    2.39
     merav
    2.38
    菹
    2.36
     auguri
    2.34
    Activations Density 0.001%

    No Known Activations