© 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. 48511
    Prev
    Next
    INDEX
    Explanations

    rec words

    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
     he
    -2.77
    or
    -2.73
    a
    -2.70
    ☫
    -2.64
    
    -2.48
    ࿊
    -2.34
    咴
    -2.34
     weiteren
    -2.31
    鹇
    -2.28
    ⟝
    -2.27
    POSITIVE LOGITS
    When
    2.88
    素晴らしい
    2.84
    With
    2.83
    Because
    2.80
    I
    2.77
    D
    2.73
     Gedanke
    2.70
    需要
    2.70
    結果
    2.59
    While
    2.58
    Activations Density 0.003%

    No Known Activations