© 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. 60683
    Prev
    Next
    INDEX
    Explanations

    words like about, in, type, such, on, use

    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
     «
    -1.35
    、「
    -1.16
    「
    -1.13
    。「
    -1.10
     می‌گوید
    -1.09
    with
    -1.07
    ității
    -1.03
    ोड़
    -0.99
     colors
    -0.99
    ，「
    -0.98
    POSITIVE LOGITS
    來
    2.16
    兩
    2.16
    立
    1.90
    利
    1.84
    度
    1.84
    行
    1.55
    數
    1.52
    力
    1.39
    了
    1.37
    論
    1.29
    Activations Density 0.160%

    No Known Activations