© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40074
    Prev
    Next
    INDEX
    Explanations

    accounting for various factors

    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
     when
    -1.61
    When
    -1.45
    when
    -1.36
     When
    -1.36
    lifier
    -1.30
    ご相談
    -1.24
    utoff
    -1.23
     focused
    -1.23
    的一部分
    -1.23
    WillAppear
    -1.21
    POSITIVE LOGITS
    lahir
    1.28
    newly
    1.27
    ışı
    1.23
    Quelle
    1.20
     trajo
    1.18
     ontstaan
    1.17
    Là
    1.16
     marcó
    1.13
     rescat
    1.13
     considér
    1.13
    Activations Density 0.069%

    No Known Activations