© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66608
    Prev
    Next
    INDEX
    Explanations

    expressing thanks

    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
     нами
    -1.27
     innovación
    -1.23
     temperatuur
    -1.21
     necesite
    -1.19
     его
    -1.17
    ではなく
    -1.16
     vanguardia
    -1.13
     techniczne
    -1.10
     ее
    -1.09
     atracción
    -1.09
    POSITIVE LOGITS
     to
    1.43
     for
    1.33
     when
    1.20
     time
    1.15
     most
    1.14
     занимается
    1.14
     phoneNumber
    1.12
    !
    1.09
    id
    1.09
    ^{-
    1.08
    Activations Density 0.017%

    No Known Activations