© 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. 10209
    Prev
    Next
    INDEX
    Explanations

    describing words followed by nouns

    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
     about
    -1.59
    Either
    -1.46
     both
    -1.26
    做
    -1.26
     that
    -1.25
     years
    -1.23
     obvious
    -1.22
     particular
    -1.21
     either
    -1.20
     Leute
    -1.20
    POSITIVE LOGITS
    стка
    1.27
    所在的
    1.25
     there
    1.24
     третий
    1.20
     Estable
    1.19
    unanje
    1.14
    祎
    1.13
    鸸
    1.13
     Pourquoi
    1.13
    蔫
    1.12
    Activations Density 0.574%

    No Known Activations