© 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. 127454
    Prev
    Next
    INDEX
    Explanations

    float numbers 0.0

    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
    outros
    -1.74
    
    -1.72
    蔓延
    -1.59
     appris
    -1.55
     regel
    -1.53
    ⎔
    -1.48
    Ҭ
    -1.46
    壜
    -1.45
     Möglich
    -1.45
    Bahkan
    -1.44
    POSITIVE LOGITS
    3
    2.00
    为何
    1.62
    2
    1.56
    "";
    1.51
     verkau
    1.49
    6
    1.48
     Aufführung
    1.48
     Übernach
    1.38
    9
    1.37
    1
    1.34
    Activations Density 0.020%

    No Known Activations