© 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. 66017
    Prev
    Next
    INDEX
    Explanations

    role or function as

    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
    As
    -1.10
     として
    -1.01
    Than
    -0.98
    作为
    -0.95
     THAN
    -0.91
    FROM
    -0.90
     trong
    -0.89
    than
    -0.89
    At
    -0.88
    kele
    -0.85
    POSITIVE LOGITS
    щие
    0.88
     sowie
    0.84
     setidaknya
    0.82
     musul
    0.81
    liste
    0.80
    섀
    0.79
    Apesar
    0.79
    ्ला
    0.78
    囡
    0.78
    ➅
    0.77
    Activations Density 0.206%

    No Known Activations