© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    the before a noun

    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
    独特的
    -1.24
     tries
    -1.23
     at
    -1.19
    点评
    -1.15
    なんですが
    -1.12
    ハウ
    -1.10
    tellation
    -1.09
    争议
    -1.09
    時間も
    -1.05
    gegevens
    -1.05
    POSITIVE LOGITS
     Arque
    1.40
     Itali
    1.39
     Terbaru
    1.35
     kutu
    1.32
     dahulu
    1.30
    ㅌ
    1.28
     Istri
    1.27
    uaire
    1.27
     spindles
    1.27
     dunque
    1.25
    Activations Density 0.062%

    No Known Activations