© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1320
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

    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
     verksam
    -1.31
     problemet
    -1.27
    or
    -1.26
    d
    -1.24
     童
    -1.24
     violento
    -1.23
     tokopedia
    -1.23
    which
    -1.22
     fantaisie
    -1.22
    Each
    -1.21
    POSITIVE LOGITS
    ción
    1.61
    们的
    1.54
    続け
    1.53
    手下
    1.50
    ことが多い
    1.48
     cet
    1.45
    ТЕЛЬ
    1.42
    {~
    1.39
    楽しむ
    1.39
    嬉しいです
    1.38
    Activations Density 0.013%

    No Known Activations