© 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. 1070
    Prev
    Next
    INDEX
    Explanations

    deserve to be

    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
    %"),
    -2.19
    ?”
    -1.95
    𝗲
    -1.91
     afectadas
    -1.91
    ândia
    -1.89
    \_\_
    -1.88
    ㆆ
    -1.84
    ornment
    -1.84
    ቺ
    -1.83
    妏
    -1.81
    POSITIVE LOGITS
    "
    3.00
    ly
    1.94
    ↵
    1.92
    s
    1.80
     概要
    1.72
     awaits
    1.71
    <
    1.70
    *
    1.67
     deserves
    1.60
    A
    1.59
    Activations Density 0.010%

    No Known Activations