© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39270
    Prev
    Next
    INDEX
    Explanations

    bottom parts

    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
    ፒ
    -1.51
    我们需要
    -1.41
    勦
    -1.38
    hinh
    -1.35
     those
    -1.27
     Häufig
    -1.27
    褴
    -1.27
    wanzig
    -1.26
     scoperta
    -1.24
    峩
    -1.24
    POSITIVE LOGITS
     of
    1.39
    ANCO
    1.36
     here
    1.27
    礎
    1.26
    : 
    1.23
    ง่าย
    1.20
     quatro
    1.19
     下
    1.18
    星座
    1.17
    IRST
    1.16
    Activations Density 0.032%

    No Known Activations