© 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. 34-GEMMASCOPE-RES-131K
    7. 82353
    Prev
    Next
    INDEX
    Explanations

    parts of 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_34/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
     miał
    -0.99
     JUST
    -0.97
    )
    -0.96
    no
    -0.94
    家が
    -0.93
    [
    -0.93
    co
    -0.92
    のは
    -0.91
     keeps
    -0.88
     all
    -0.88
    POSITIVE LOGITS
    Einstellungen
    1.17
    Elaboración
    1.11
    みなさま
    1.10
    鴬
    1.09
     незавер
    1.09
    importante
    1.08
    ＊＊＊＊
    1.08
    。)
    1.05
     eventuell
    1.05
    Trama
    1.03
    Activations Density 0.542%

    No Known Activations