© 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. 42423
    Prev
    Next
    INDEX
    Explanations

    float2, xy, z coordinates

    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
     parlato
    -1.23
     można
    -1.23
     mục
    -1.19
    '][]
    -1.16
    Ꮠ
    -1.09
     angebra
    -1.09
     sowas
    -1.05
    ܊
    -1.05
     dahin
    -1.04
     científicas
    -1.03
    POSITIVE LOGITS
     I
    1.30
    对你
    1.04
    Deskripsi
    1.03
    讶
    1.00
     actuelle
    0.99
     karena
    0.97
    gered
    0.97
    介意
    0.97
     שם
    0.96
    讓你
    0.96
    Activations Density 0.088%

    No Known Activations