© 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. 74785
    Prev
    Next
    INDEX
    Explanations

    is a structure

    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
     for
    -1.50
     which
    -1.41
     homme
    -1.32
    /}
    -1.27
     >=",
    -1.24
    an
    -1.24
    ły
    -1.23
     по
    -1.22
    ské
    -1.21
    ativi
    -1.21
    POSITIVE LOGITS
     its
    1.88
     diferite
    1.61
     distribuir
    1.55
     condenado
    1.55
    ditionally
    1.55
     estaremos
    1.52
     bloquear
    1.45
     incluem
    1.44
     anunció
    1.41
     aislada
    1.39
    Activations Density 0.415%

    No Known Activations